Kolais in the Sales Force Automation Industry

Kola

kola

This paper is available on arxiv under CC BY-SA 4.0 DEED license. Authors: (1) Tomáš Jakl, Czech Academy of Sciences and Czech Technical University; (2) Dan Marsden, School of Computer Science University of Nottingham; (3) Nihil Shah, Department of Computer Science University of Oxford. Table of Links Abstract & Introduction Prelimenaries FVM Theorems for Positive Existential Fragments FVM Theorems for Counting Logic FVM Theorems for The Full Logic Abstract FVM Theorems for Products Adding Equality and Other Enrichment Conclusions, Acknowledgments & References Appendix A FVM theorems for coproducts Appendix B Proofs Omitted from Section III Appendix C Proofs Omitted from Section IV Appendix D Proofs Omitted from Section V Appendix E Proofs Omitted from Section VI Appendix F Proofs Omitted from Section VII VIII. CONCLUSION We presented a categorical approach to the composition method, and specifically Feferman–Vaught–Mostowski theorems. We exploit game comonads to encapsulate the logics and their model comparison games. Surprising connections to classical constructions in category theory, and especially the monad theory of bilinear maps emerged from this approach, cf. Section V-A. For finite model theorists, our work provides a novel highlevel account of many FVM theorems, abstracting away from individual logics and constructions. Furthermore, concrete instances of these theorems are verified purely semantically, by finding a suitable collection homomorphisms forming a Kleisli law satisfying (S2’), instead of the usual delicate verification that strategies of model comparison games compose. For game comonads, we provide a much needed tool that enables us to handle logical relationships between structures as they are transformed or viewed in terms of different logics. The FVM results in this paper, combined with judicious use of the techniques described in Section VII can be pushed significantly further. FVM theorems and the compositional method are of particular significance in the setting of monadic second-order (MSO) logic [49]. Exploiting the results we have presented for the composition method, a follow up paper will give a comonadic semantics for MSO, and develop a semantic account of Courcelle’s algorithmic meta-theorems [5]. The original theorem of Feferman–Vaught [3] is very flexible, including incorporating structure on the indices of families of models to be combined by an operation, as well as the models themselves. This aspect is currently outside the scope of our comonadic methods. An ad-hoc adaptation of our approach also gives a proof of the FVM theorem for free amalgamations, but this does not follow directly from our theorems. Developing these extensions is left to future work. The present work bears some resemblance to Turi and Plotkin’s bialgebraic semantics [50], a categorical model of structural operational semantics (SOS) [51]. Turi and Plotkin noticed that the SOS rules assigning behaviour to syntax could be abstracted as a certain distributive law λ. An algebra encodes the composition operations of the syntax, and a coalgebra the behaviour. If this pair is suitably compatible with λ, forming a so-called λ-bialgebra, then crucially bisimulation is a congruence with respect to the composition operations. Both bialgebraic semantics and our work presented in this paper give a categorical account of well-behaved composition operations, with the interaction between composition and observable behaviour mediated by some form of distributive law. There are also essential differences: bialgebraic semantics typically focuses on assigning behaviour to syntax, whereas FVM theorems encompass operations on models. Our FVM theorems are parametric in a choice of logic or observable behaviour, while the notion of bisimulation in bialgebraic semantics is fixed by the coalgebra signature functor. The natural presence of positive existential and counting quantifier variants of FVM theorems, and the incorporation of resource parameters, do not seem to have a direct analogue in bialgebraic semantics. The similarities are intriguing, and exploring the relationship between bialgebraic semantics and our approach to FVM theorems is left to future work. We would like to thank Clemens Berger for suggesting the connection with parametric adjoints and Nathanael Arkor for his suggestions on terminology. We are also grateful to the members of the EPSRC project “Resources and co-resources” for their feedback. Acknowledgements: REFERENCES [1] L. Libkin, Elements of finite model theory. Springer, 2004, vol. 41. [2] A. Mostowski, “On direct products of theories,” The Journal of Symbolic Logic, vol. 17, no. 1, pp. 1–31, 1952. [3] S. Feferman and R. L. Vaught, “The first-order properties of algebraic systems,” Fundamenta Mathematicae, vol. 47, 1959. [4] J. A. Makowsky, “Algorithmic uses of the Feferman–Vaught theorem,” Annals of Pure and Applied Logic, vol. 126, no. 1-3, pp. 159–213, 2004. [5] B. Courcelle and J. Engelfriet, Graph structure and monadic secondorder logic: a language-theoretic approach. Cambridge University Press, 2012, vol. 138. [6] A. Ehrenfeucht, “An application of games to the completeness problem for formalized theories,” Fundamenta mathematicae, vol. 49, no. 129- 141, p. 13, 1960. [7] R. Fraïssé, “Sur quelques classifications des relations, basées sur des isomorphismes restreints,” Publications Scientifiques de l’Université d’Alger. Série A (mathématiques), vol. 2, pp. 273–295, 1955. [8] P. G. Kolaitis and M. Y. Vardi, “Infinitary logics and 0–1 laws,” Information and computation, vol. 98, no. 2, pp. 258–294, 1992. [9] M. Hennessy and R. Milner, “On observing nondeterminism and concurrency,” in International Colloquium on Automata, Languages, and Programming. Springer, 1980, pp. 299–309. [10] S. Abramsky, A. Dawar, and P. Wang, “The pebbling comonad in finite model theory,” in 32nd Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2017, Reykjavik, Iceland, June 20-23, 2017. IEEE Computer Society, 2017, pp. 1–12. [11] S. Abramsky and N. Shah, “Relating structure and power: Comonadic semantics for computational resources,” Journal of Logic and Computation, vol. 31, no. 6, pp. 1390–1428, 2021. [12] E. Moggi, “Computational lambda-calculus and monads,” in Proceedings of the Fourth Annual Symposium on Logic in Computer Science (LICS ’89), Pacific Grove, California, USA, June 5-8, 1989. IEEE Computer Society, 1989, pp. 14–23. [13] ——, “Notions of computation and monads,” Information and Computation, vol. 93, no. 1, pp. 55–92, 1991. [14] E. G. Manes, Algebraic theories. Springer Science, 1976, vol. 26. [15] S. Abramsky and D. Marsden, “Comonadic semantics for guarded fragments,” in 36th Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2021, Rome, Italy, June 29 - July 2, 2021. IEEE, 2021, pp. 1–13. [16] A. Ó. Conghaile and A. Dawar, “Game comonads & generalised quantifiers,” in 29th EACSL Annual Conference on Computer Science Logic, CSL 2021, January 25-28, 2021, Ljubljana, Slovenia (Virtual Conference), ser. LIPIcs, C. Baier and J. Goubault-Larrecq, Eds., vol. 183. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2021, pp. 16:1–16:17. [17] Y. Montacute and N. Shah, “The pebble-relation comonad in finite model theory,” in LICS ’22: 37th Annual ACM/IEEE Symposium on Logic in Computer Science, Haifa, Israel, August 2 - 5, 2022, C. Baier and D. Fisman, Eds. ACM, 2022, pp. 13:1–13:11. [Online]. Available: https://doi.org/10.1145/3531130.3533335 [18] T. Paine, “A pebbling comonad for finite rank and variable logic, and an application to the equirank-variable homomorphism preservation theorem,” in Proceedings of the 36th Conference on the Mathematical Foundations of Programming Semantics, MFPS 2020, Online, October 1, 2020, ser. Electronic Notes in Theoretical Computer Science, P. Johann, Ed., vol. 352. Elsevier, 2020, pp. 191–209. [19] A. Dawar, T. Jakl, and L. Reggio, “Lovász-type theorems and game comonads,” in 36th Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2021, Rome, Italy, June 29 - July 2, 2021. IEEE, 2021, pp. 1–13. [20] S. Abramsky and D. Marsden, “Comonadic semantics for hybrid logic,” in 47th International Symposium on Mathematical Foundations of Computer Science, MFCS 2022, August 22-26, 2022, Vienna, Austria, ser. LIPIcs, S. Szeider, R. Ganian, and A. Silva, Eds., vol. 241. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2022, pp. 7:1–7:14. [21] L. Reggio, “Polyadic sets and homomorphism counting,” Advances in Mathematics, vol. 410, p. 108712, 2022. [22] S. Abramsky, “Structure and power: an emerging landscape,” Fundam. Informaticae, vol. 186, no. 1-4, pp. 1–26, 2022. [23] S. Abramsky and L. Reggio, “Arboreal categories and resources,” in 48th International Colloquium on Automata, Languages, and Programming, ICALP 2021, July 12-16, 2021, Glasgow, Scotland (Virtual Conference), ser. LIPIcs, N. Bansal, E. Merelli, and J. Worrell, Eds., vol. 198. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2021, pp. 115:1–115:20. [24] H. Ebbinghaus and J. Flum, Finite model theory, ser. Perspectives in Mathematical Logic. Springer, 1995. [25] E. G. Manes and P. Mulry, “Monad compositions I: general constructions and recursive distributive laws,” Theory and Applications of Categories, vol. 18, no. 7, pp. 172–208, 2007. [26] A. Kock, “Bilinearity and cartesian closed monads,” Mathematica Scandinavica, vol. 29, no. 2, pp. 161–174, 1971. [27] T. Jakl, D. Marsden, and N. Shah, “Generalizations of bilinear maps,” 2022, technical report, arXiv preprint. [Online]. Available: https://arxiv.org/abs/2205.05382 [28] A. Dawar, S. Severini, and O. Zapata, “Pebble games and cospectral graphs,” Electronic Notes in Discrete Mathematics, vol. 61, pp. 323– 329, 2017. [29] S. Abramsky and N. Tzevelekos, “Introduction to categories and categorical logic,” in New structures for physics. Springer, 2010, pp. 3–94. [30] S. Awodey, Category theory. Oxford University Press, 2010. [31] C. Stirling, Modal and temporal properties of processes. Springer Science & Business Media, 2001. [32] A. W. Roscoe, Understanding concurrent systems. Springer Science & Business Media, 2010. [33] H. Kleisli, “Every standard construction is induced by a pair of adjoint functors,” Proceedings of the American Mathematical Society, vol. 16, no. 3, pp. 544–546, 1965. [34] B. Jacobs, “Semantics of weakening and contraction,” Annals of Pure and Applied Logic, vol. 69, no. 1, pp. 73–106, 1994. [35] S. Abramsky, T. Jakl, and T. Paine, “Discrete density comonads and graph parameters,” in Coalgebraic Methods in Computer Science - 16th IFIP WG 1.3 International Workshop, CMCS 2022, Colocated with ETAPS 2022, Munich, Germany, April 2-3, 2022, Proceedings, ser. Lecture Notes in Computer Science, H. H. Hansen and F. Zanasi, Eds., vol. 13225. Springer, 2022, pp. 23–44. [Online]. Available: https://doi.org/10.1007/978-3-031-10736-8_2 [36] P. T. Johnstone, “Adjoint lifting theorems for categories of algebras,” Bulletin of the London Mathematical Society, vol. 7, no. 3, pp. 294– 297, 1975. [37] A. Kock, “Closed categories generated by commutative monads,” Journal of the Australian Mathematical Society, vol. 12, no. 4, pp. 405–424, 1971. [38] G. Seal, “Tensors, monads and actions,” Theory and Applications of Categories, vol. 28, no. 15, pp. 403–434, 2013. [39] F. E. Linton, “Coequalizers in categories of algebras,” in Seminar on triples and categorical homology theory. Springer, 1969, pp. 75–90. [40] R. Street, “The petit topos of globular sets,” Journal of Pure and Applied Algebra, vol. 154, no. 1-3, pp. 299–315, 2000. [41] M. Weber, “Generic morphisms, parametric representations and weakly cartesian monads,” Theory and Applications of Categories, vol. 13, no. 14, pp. 191–234, 2004. [42] ——, “Familial 2-functors and parametric right adjoints,” Theory and Applications of Categories, vol. 18, no. 22, pp. 665–732, 2007. [43] C. Berger, P.-A. Mellies, and M. Weber, “Monads with arities and their associated theories,” Journal of Pure and Applied Algebra, vol. 216, no. 8-9, pp. 2029–2048, 2012. [44] T. Altenkirch, J. Chapman, and T. Uustalu, “Monads need not be endofunctors,” in International Conference on Foundations of Software Science and Computational Structures. Springer, 2010, pp. 297–311. [45] P. J. Freyd and G. M. Kelly, “Categories of continuous functors, I,” Journal of Pure and Applied Algebra, vol. 2, no. 3, pp. 169–191, 1972. [46] B. Bednarczyk and M. Urbanczyk, “Comonadic semantics for description logics games,” in Proceedings of the 35th International Workshop on Description Logics (DL 2022) co-located with Federated Logic Conference (FLoC 2022), Haifa, Israel, August 7th to 10th, 2022, ser. CEUR Workshop Proceedings, O. Arieli, M. Homola, J. C. Jung, and M. Mugnier, Eds., vol. 3263. CEUR-WS.org, 2022. [Online]. Available: http://ceur-ws.org/Vol-3263/paper-5.pdf [47] M. Bojanczyk, “Separator logic and star-free expressions ´ for graphs,” 2021, arXiv preprint. [Online]. Available: https://arxiv.org/abs/2107.13953 [48] N. Schirrmacher, S. Siebertz, and A. Vigny, “First-Order Logic with Connectivity Operators,” in 30th EACSL Annual Conference on Computer Science Logic (CSL 2022), ser. Leibniz International Proceedings in Informatics (LIPIcs), F. Manea and A. Simpson, Eds., vol. 216. Dagstuhl, Germany: Schloss Dagstuhl – LeibnizZentrum für Informatik, 2022, pp. 34:1–34:17. [Online]. Available: https://drops.dagstuhl.de/opus/volltexte/2022/15754 [49] Y. Gurevich, “Monadic second-order theories,” in Model-theoretic logics, J. Barwise and S. Feferman, Eds. Cambridge University Press, 1985, pp. 479–506. [50] D. Turi and G. Plotkin, “Towards a mathematical operational semantics,” in Proceedings of Twelfth Annual IEEE Symposium on Logic in Computer Science. IEEE, 1997, pp. 280–291. [51] G.D.Plotkin, “A structural approach to operational semantics,” Aarhus University, Tech. Rep. DAIMI FN-19, 1981. [52] J. Adámek, J. Adamek, J. Rosicky et al., Locally presentable and accessible categories. Cambridge University Press, 1994, vol. 189.

A Categorical Account of
Composition Methods in Logic: Conclusions, Acknowledgments & References

Back in 2020, 's brand was worth a whopping , while PepsiCo's brand was valued at $70.9 billion. The time-honored competition between Pepsi and Coca-Cola is legendary in marketing, still influencing the drink market, global marketing, peoples’ choice of product, and brand loyalty. For over a century, this battle has evolved from a taste test to today’s online advertisement. This article delves into the creativity and strategies Pepsi and Coca-Cola implore to win customers worldwide; in this article, we will examine their battles, advertisement strategies, and how they adjust to changing customer tastes to keep their storied rivalry living. Coca-Cola $84.86 billion Background In , Coca-Cola first came to life. It all began when Dr. John S. Pemberton, a pharmacist, created a soft drink that had a unique taste meant to be sold at soda fountains. Frank Robinson his bookkeeper named the drink “Coca-Cola” and also crafted the logo in his handwriting; Coca-Cola was publicized as a stress-relieving drink. 1886, in Atlanta, Georgia On the other hand, in , Pepsi originally called “Brad’s Drink” was created by Caleb Bradham a pharmacist from New Bern, North Carolina. Brad’s Drink was later renamed Pepsi-cola in 1893, this change of name was inspired by the digestive aid; pepsin, and kola nuts which were used in the recipe. Pepsi was promoted as a tasty and healthy digestion-aiding beverage. 1893 \When Coca-Cola started its marketing journey, emphasis was laid on how refreshing and satisfactory it was. The brand was ahead of the game as it was the first to use branded merchandise, by distributing items like calendars and clocks with their logos on it to promote their brand. In 1916 Coca-Cola decided to switch up its marketing tactics with the introduction of the popular bottle shape; this made it different, and more recognizable in different places. In 1927 they created the largest soda fountain in the world. At first, Pepsi started by promoting its health benefits, strategically placing itself as a digestive aid. During the great depression that occurred in the 1930s, Pepsi became popular for selling double the amount of soda for the same price as Coca-Cola ( that is, 12 ounces of the beverage for the same price as 6 ounces of Coca-Cola) this became their unique selling point.             Pepsi came up with another approach in the 1960s which was the “Pepsi Generation” campaign,  they tried connecting with younger people; this act was the starting point of the famous Cola wars with Coca-Cola. Key Marketing Battles In the famous taste battle between Pepsi and Coke, the numbers show who's winning. In 2020, Coke had a big chunk of the market, with . This tells us a lot about what people like and how loyal they are to these brands. 43.7%, while Pepsi had 24.1% The Cola Wars represents one of the most notable marketing showdowns in marketing history, embodied by the Pepsi generation campaign. It all began in the year 1975 when Pepsi organized a blind taste test to see which product people liked better, Pepsi or Coca-Cola. This made Pepsi very famous, Coca-Cola could not just watch but felt the need to do something. In 1985, Coca-Cola responded by changing its recipe to “ ”, this move had no positive outcome; eventually they brought back their original recipe and called it “Coca-Cola Classic”. It was a valuable learning experience for both companies. New Coke Right from time, backing up a product with a famous person has always been a powerful marketing tool, companies believe that having a celebrity support a particular product will make people have more interest in it. Pepsi and Coca-Cola have thoroughly utilized these tactics, and prominent figures like Michael Jackson and Britney Spears have endorsed Pepsi. On the one hand, Coca-Cola has endorsed icons like Selena Gomez, Marilyn Monroe, and others recently. These endorsements, not only boost the brand’s visibility; it also contribute to shaping its identity by connecting it with the irresistible appeal and charisma of celebrities that support them. Lately, staying healthy has been a priority for a lot of people, companies like Pepsi and Coca-Cola have taken note of this, and they have adapted to this trend by expanding their options, adding healthier choices like juice, water, and drinks that contain fewer calories; their advertisements are also changing emphasizing the nutritional value of these products. This change highlights how important it is for companies to keep the needs of people in mind. Comparative Analysis of Marketing Strategies At first, Marketing was usually all about reaching large groups of people based on age, gender, and income. However, today’s marketing is about targeting specific individuals and customizing messages just for them. Companies now make use of data analytics to figure out people’s interests and behaviors, and then send messages that resonate. Change like this reflects an understanding that in a diverse world, a generic approach will not be effective because people's preferences cannot be the same in a globalized market. Over time, advertising has changed. At the start we used to see ads on traditional platforms like TV and newspapers, now we see them on the internet and social media; every form of advertisement has its benefits. TV ads reach a large group of people while online advertisements reach specific individuals only. Social media has changed marketing a lot, companies can now reach their customers right away and get feedback; the best part is with online advertisement we can measure how well it works through metrics like clicks and shares. With this, companies can identify areas for improvement and adjust their ads to get good results. Brands' messaging and positioning have gone through massive change too, in the past, Brands only emphasized their products’ features and benefits. But now through storytelling, they create an emotional connection with people; they do not want to be just providers of goods and services alone, they want to be like friends who share the same dreams, values, and worries. This is about building strong bonds with people and fostering dedication even in a saturated market. Iconic Campaigns and Their Impact In the 1980s, Pepsi came up with a brilliant idea called the “ ” It was a blind taste test where people did not know which of the sodas they were drinking, Pepsi or Coca-Cola. This was a daring move that boosted Pepsi's sales and positioned it as a confident, unconventional, youth-oriented brand. Another remarkable campaign was “The Choice of a New Generation”, this campaign featured celebrities of that time making Pepsi much cooler for younger people. Pepsi Challenge On the other hand, Coca-Cola has a natural talent for creating campaigns that make us feel warm and connected. Remember the ” ” campaign? Which featured bottles with customized names, it made buying a soda feel so personal and fun. It strengthened  Coca-Cola as a brand that was about bringing people together. Who can forget those Christmas trucks? “ ” ads always marked the start of a festive season, making us feel very excited; Coca-Cola sure knows how to spread happiness and celebration. Share a Coke The holidays are coming The way people see Pepsi and Coca-Cola was influenced by these advertising efforts. Pepsi is known as a brand that is cool and daring, having a desire to challenge existing ways of doing things and exploring new possibilities. Coca-Cola, conversely has positioned itself as a classic symbol that brings people together, making moments happier and more enjoyable. The Role of Innovation in Marketing When a new product is launched it captures people's attention, and brings excitement; using initiative marketing techniques like sneak pics and collaborating with famous people makes the whole experience very exciting. The packaging of a product is not just about aesthetics; it is about making sure they are easy to use, suitable for the environment, and gives a pleasant experience when it is being unboxed.  Coca-Cola bottles with people's names on them or Amazon user-friendly packaging can be taken as an example; it shows how packaging can make a brand look unique and influence consumers' preferences. The way brands connect with people has changed through digital marketing, they now make use of social media platforms, super cool digital encounters, and customized emails making the connection with consumers more personal and fun. Nike uses AR to launch their sneakers, and Spotify makes playlists just for you;  using new technologies to make memorable experiences that people love, makes customers stay loyal to the brand. Global Reach and Localization Strategies Coca-Cola and Pepsi are experts at adjusting their marketing tactics to fit different global markets. They don't just translate words they also change colors, themes, and messaging to match different local cultures. Coca-Cola's “ ” campaign was themed universally around joy and being together; local celebrities were featured and things in cultural reference to different cultures were also used to make the connection feel more personal for the people there. Open Happiness Understanding and respecting cultural differences is crucial. Coca-Cola and Pepsi have learned this aspect; Pepsi's journey to India is a good example, during Pepsi's expansion into India they didn't just advertise their product but also engaged in a big part of the Indian culture which was cricket. This way, they became an integral part of Indian recreation activities. Coca-Cola's strategy in China shows that adapting to local culture can be successful, They incorporated Chinese symbols and partnered with popular artists to be well-known to Chinese people. Conversely, Pepsi had issues with the Philippines because of a branding mistake that did not respect their local custom. This highlights the challenges that follow global marketing. The Current State of Battle Pepsi has relied heavily on entertainment, teaming up with notable stars and important occasions to win young people over. Focusing on digital platforms and social media engagements allowed them to create interactive and viral content that gets people talking and sharing online. On the other hand, Coca-Cola focuses on that give people a feeling of joy, togetherness, and shared experience; their “open happiness” and Share a Coke” can be used as an example, it has been successful in promoting a positive brand image across different regions. emotional branding with campaigns Regardless of the competition, Coca-Cola maintains a lead worldwide because its brand is loved by people wherever you go. However, Pepsi is making major progress in certain markets by offering healthier snacks and drinks people want currently. Both Pepsi and Coca-Cola have dedicated fans though customers are leaning toward healthier, low-sugar, and eco-friendly alternatives. In the future, Pepsi and Coca-Cola are striving to be more than just companies that make drinks. Coca-Cola is working hard to be eco-friendly by reducing its emissions and making its packaging easier to reutilize. Meanwhile, Pepsi is also big on sustainability but is investing in digital technology to make sure customers have a wonderful experience with their brand. Final Thoughts The Pepsi vs. Coca-Cola clashes teach us an invaluable lesson about outperforming in marketing. These brands have been struggling for ages, changing their strategies constantly to stay relevant; from creative ads to digital excitement. They have adjusted to what people care about, their rivalry is not just about the products, it is all about the fluid nature of marketing. Watching them, we learn how brands can continue to develop and connect with customers,  now and in the years to come.

Pepsi vs Coca-Cola: A Marketing Battle for the Ages

In this blog post, I will share how to use LangChain, a flexible framework for building AI-driven applications, to extract and generate structured JSON data with GPT and Langchain. I'll provide code snippets and concise instructions to help you set up and run the project. You can find the code for this tutorial on GitHub: . link About LangChain LangChain is a framework designed to speed up the development of . It provides a suite of components for crafting prompt templates, connecting to diverse data sources, and interacting seamlessly with various tools. It simplifies prompt engineering, data input and output, and tool interaction so we can focus on core logic. It is available in and JavaScript. AI-driven applications Python LangChain contains tools that make getting structured (as in JSON format) output out of LLMs easy. Let's use them to our advantage. Installing and Setup I am assuming you have one of the latest versions of Python. I've used 3.11. Visit the LangChain website if you need more details. First, create a new project, i.e.: Create a new directory for your project and navigate to it in your terminal. Run pip install langchain openai Create an file. index.py Then, let's configure the API keys. Other dependencies are included. # configure credentials (easiest)
export OPENAI_API_KEY=XXX This is just for demonstrative use. In production, use your secret management way of choice. Let's import the required dependencies on top of our Python file. import os
from langchain.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
from langchain.chat_models import ChatOpenAI

from langchain.output_parsers import PydanticOutputParser
from pydantic import BaseModel, Field
from typing import List Generating data Let's start with generating some fake data to see the possibilities of parsing. Sample use case: JSON output formatting for fake identity generation. Output schema definition First, we need to tell the library what we want to get. LangChain supports defining expected schema using a popular library, Pydantic: # Define a new Pydantic model with field descriptions and tailored for Twitter.
class TwitterUser(BaseModel):
    name: str = Field(description="Full name of the user.")
    handle: str = Field(description="Twitter handle of the user, without the '@'.")
    age: int = Field(description="Age of the user.")
    hobbies: List[str] = Field(description="List of hobbies of the user.")
    email: str = Field(description="Email address of the user.")
    bio: str = Field(description="Bio or short description about the user.")
    location: str = Field(description="Location or region where the user resides.")
    is_blue_badge: bool = Field(
        description="Boolean indicating if the user has a verified blue badge."
    )
    joined: str = Field(description="Date the user joined Twitter.")
    gender: str = Field(description="Gender of the user.")
    appearance: str = Field(description="Physical description of the user.")
    avatar_prompt: str = Field(
        description="Prompt for generating a photorealistic avatar image. The image should capture the essence of the user's appearance description, ideally in a setting that aligns with their interests or bio. Use professional equipment to ensure high quality and fine details."
    )
    banner_prompt: str = Field(
        description="Prompt for generating a banner image. This image should represent the user's hobbies, interests, or the essence of their bio. It should be high-resolution and captivating, suitable for a Twitter profile banner."
    ) Prompt template To use the auto-generated template, we need to create a LangChain construct called PromptTemplate. In this case, we're going to use variation appropriate for a cheap chat model like . It will contain format instructions from the parser: GPT 3.5 # Instantiate the parser with the new model.
parser = PydanticOutputParser(pydantic_object=TwitterUser)

# Update the prompt to match the new query and desired format.
prompt = ChatPromptTemplate(
    messages=[
        HumanMessagePromptTemplate.from_template(
            "answer the users question as best as possible.\n{format_instructions}\n{question}"
        )
    ],
    input_variables=["question"],
    partial_variables={
        "format_instructions": parser.get_format_instructions(),
    },
) Try it out To execute the structured output, call the OpenAI model with the input: chat_model = ChatOpenAI(
    model="gpt-3.5-turbo",
    openai_api_key=os.getenv("OPENAI_API_KEY"),
    max_tokens=1000
)

# Generate the input using the updated prompt.
user_query = (
    "Generate a detailed Twitter profile of a random realistic user with a diverse background, "
    "from any country in the world, original name, including prompts for images. Come up with "
    "real name, never use most popular placeholders like john smith and john doe."
)
_input = prompt.format_prompt(question=user_query)

output = chat_model(_input.to_messages())
parsed = parser.parse(output.content)
print(output.content)
print(parsed) Here's what will be sent to the AI model. This will most likely change in the future LangChain versions. Answer the user query.
The output should be formatted as a JSON instance that conforms to the JSON schema below.

As an example, for the schema {"properties": {"foo": {"title": "Foo", "description": "a list of strings", "type": "array", "items": {"type": "string"}}}, "required": ["foo"]}
the object {"foo": ["bar", "baz"]} is a well-formatted instance of the schema. The object {"properties": {"foo": ["bar", "baz"]}} is not well-formatted.

Here is the output schema:

{"properties": {"name": {"description": "Full name of the user.", "title": "Name", "type": "string"}, "handle": {"description": "Twitter handle of the user, without the '@'.", "title": "Handle", "type": "string"}, "age": {"description": "Age of the user.", "title": "Age", "type": "integer"}, "hobbies": {"description": "List of hobbies of the user.", "items": {"type": "string"}, "title": "Hobbies", "type": "array"}, "email": {"description": "Email address of the user.", "title": "Email", "type": "string"}, "bio": {"description": "Bio or short description about the user.", "title": "Bio", "type": "string"}, "location": {"description": "Location or region where the user resides.", "title": "Location", "type": "string"}, "is_blue_badge": {"description": "Boolean indicating if the user has a verified blue badge.", "title": "Is Blue Badge", "type": "boolean"}, "joined": {"description": "Date the user joined Twitter.", "title": "Joined", "type": "string"}, "gender": {"description": "Gender of the user.", "title": "Gender", "type": "string"}, "appearance": {"description": "Physical description of the user.", "title": "Appearance", "type": "string"}, "avatar_prompt": {"description": "Prompt for generating a photorealistic avatar image. The image should capture the essence of the user's appearance description, ideally in a setting that aligns with their interests or bio. Use professional equipment to ensure high quality and fine details.", "title": "Avatar Prompt", "type": "string"}, "banner_prompt": {"description": "Prompt for generating a banner image. This image should represent the user's hobbies, interests, or the essence of their bio. It should be high-resolution and captivating, suitable for a Twitter profile banner.", "title": "Banner Prompt", "type": "string"}}, "required": ["name", "handle", "age", "hobbies", "email", "bio", "location", "is_blue_badge", "joined", "gender", "appearance", "avatar_prompt", "banner_prompt"]}

Generate a detailed Twitter profile of a random realistic user with a diverse background, from any country in the world, original name, including prompts for images. Come up with real name, never use most popular placeholders like john smith and john doe. The output from the model will look like this: {
    "name": "Daniela Kolarova",
    "handle": "PragueReveries",
    "age": 29,
    "hobbies": ["classical piano", "literature", "yoga"],
    "email": "daniela.kolarova@czmail.cz",
    "bio": "Finding harmony through keys, books, and breaths. Embracing Prague's spellbinding tales.",
    "location": "Prague, Czech Republic",
    "is_blue_badge": True,
    "joined": "2014-05-01",
    "gender": "female",
    "appearance": "Caucasian, long wavy auburn hair, green eyes, 5'6\"",
    "avatar_prompt": "Photorealistic image of a caucasian woman with green eyes, playing a grand piano. Use Olympus PEN-F with a 38mm lens.",
    "banner_prompt": "High-resolution depiction of Prague's rooftops, cozy libraries, and serene yoga studios. Samsung Galaxy S20 II.",
} As you can see, we got just what we needed. We can generate whole identities with complex descriptions matching other parts of the persona. Error handling You may wonder if is safe in any way. using LLM in a production application If, for example, the output was missing a name, we would get this error: Got: 1 validation error for TwitterUser
name
  none is not an allowed value (type=type_error.none.not_allowed) Luckily, LangChain is focused on problems just like this. In case the output needs fixing, use the OutputFixingParser. It will try and fix errors in case your LLM outputs something that does not match your requirements. from langchain.output_parsers import OutputFixingParser
from langchain.schema import OutputParserException

try:
    parsed = parser.parse(output.content)
except OutputParserException as e:
    new_parser = OutputFixingParser.from_llm(
        parser=parser,
        llm=ChatOpenAI()
    )
    parsed = new_parser.parse(output.content) Under the hood, LangChain is calling our LLM again to fix the output. Extracting Data from Files To load and extract data from files using LangChain, you can follow these steps. In this example, we're going to load the PDF file. Conveniently, LangChain has utilities just for this purpose. We need one extra dependency. pip install pypdf We're going to load a short bio of Elon Musk and extract the information we've previously generated. Download the PDF file here: . google drive from langchain.document_loaders import PyPDFLoader

loader = PyPDFLoader("elon.pdf")
document = loader.load() We need to modify the prompt template to indicate extraction, not generation. document_query = "Create a profile based on this description: " + document[0].page_content

_input = prompt.format_prompt(question=document_query)
output = chat_model(_input.to_messages())
parsed = parser.parse(output.content)

print(parsed) Thanks to these modifications, we get the following output: {
  "name": "Elon Musk",
  "handle": "elonmusk",
  "age": 51,
  "hobbies": ["space exploration", "electric vehicles", "artificial intelligence", "sustainable energy", "tunnel construction", "neural interfaces", "Mars colonization", "hyperloop transportation"],
  "email": "elonmusk@gmail.com",
  "bio": "Entrepreneur, inventor, and CEO. Revolutionizing transportation and energy.",
  "location": "Pretoria, South Africa",
  "is_blue_badge": false,
  "joined": "2008-06-02",
  "gender": "male",
  "appearance": "normal build, short-cropped hair, trimmed beard",
  "avatar_prompt": "Generate a photorealistic avatar image capturing Elon Musk's appearance. The image should align with his interests and bio.",
  "banner_prompt": "Generate a high-resolution banner image representing Elon Musk's various fields of interest."
} By following these steps, we've extracted structured JSON data from a PDF file! This approach is versatile and can be adapted to suit your specific use case. Conclusion In conclusion, by leveraging , we can reduce the complexity of our LLM apps and introduce useful error handling. LangChain, GPTs, and Python You can find the code for this tutorial on GitHub: . link Subscribe to my profile by filling in your email address on the left, and be up-to-date with my articles! Don't forget to follow me on Twitter @ and subscribe to my blog for more tips and insights! horosin_ newsletter If you don't have Twitter, you can also follow me on . LinkedIn Also published . here

Unlocking Structured JSON Data with LangChain and GPT: A Step-by-Step Tutorial

A wide array of useful digital tools is available without cost, for anyone. Passionate developers and volunteers make this possible in the environment of open-source software, but there’s not much they gain in exchange for it. These projects are often struggling to find funding to keep afloat, and that’s where the Kivach platform in Obyte may help. is a pioneering open-source cascading donations platform designed to empower individuals and organizations to fundraise for various causes efficiently and transparently. It operates on the principle of "cascading donations," Kivach where donations received on GitHub can be distributed across multiple projects or recipients. This is because those recipients can donate a part or a total of the coins to any other open-source project(s) they want on GitHub, automatically. So, the donations can flow as a cascade across multiple repositories and collaborators. Kivach offers a user-friendly interface, allowing users to allocate funds in cryptocurrencies to specific initiatives, fostering a community-driven approach to philanthropy. All that the contributors need is an Obyte wallet, some crypto funds, and the name of the GitHub repository. Let’s explore some of them to donate! GIMP (GNU Image Manipulation Program) GIMP (from General Image Manipulation Program) was released in 1998 by Spencer Kimball and Peter Mattis. , rivaling commercial software like Adobe Photoshop. Its capabilities include image retouching, photo enhancement, and even support for advanced techniques like layers, masks, and filters. It’s a robust open-source software used for graphic design and image editing This tool supports various file formats, including PSD, and offers extensive customization options with a plethora of plugins and extensions. It's a favorite among graphic designers, photographers, illustrators, and hobbyists alike, offering professional-grade tools for free. Currently, it’s mainly maintained by the developers “Jehan” and Øyvind Kolås. Jehan is the main developer, and he’s creating (and raising funds for) an animation movie named , along with the artist Aryeom. ZeMarmot Of course, they to keep working on the project. They appear as . Remember that it’s important to tell them about the donation, though, so they can claim it with their own —a pre-existing one or a new one. accept donations To avoid Patreon fees, you can donate through Kivach with cryptocurrencies. Gnome/Gimp Obyte wallet Blender (3D Modeling) This is a versatile and open-source 3D computer graphics software used for a wide range of applications, including 3D modeling, animation, rendering, compositing, and more. Released initially in January 1994 as an in-house application by the Dutch animation studio NeoGeo, Blender became open-source in 2002, allowing users worldwide to contribute to its development. Blender's development is led by the Blender Foundation, a non-profit organization that oversees the project's direction and ensures its commitment to open-source principles. It has a global community of developers, artists, and enthusiasts who continually refine and enhance the software. Blender has gained immense popularity for its professional-grade features, i ncluding support for character animation, physics simulations, and a powerful node-based compositor. To support Blender financially, users can support the , where donations can be made to directly fund the software's development. Contributions are used to pay developers, support infrastructure, and ensure Blender's continued growth and improvement. They accept Bitcoin (BTC), Bitcoin Cash (BCH), Ethereum (ETH), and Litecoin (LTC). In Kivach, they’re available as . Blender Development Fund blender/blender Kdenlive (Video Editor) This is an open-source video editing software that offers a comprehensive and user-friendly platform for video editing and post-production. It was first released in 2002 by Jason Wood and has since evolved into Kdenlive is known for its intuitive interface and robust feature set, including support for multiple video and audio tracks, transitions, effects, and a wide range of video formats. a powerful video editing tool for Linux and other Unix-like operating systems. Its development is driven by a community of passionate contributors and developers who work collaboratively to enhance its functionality and performance. The project is part of the larger KDE Community, which promotes several open-source software projects, including . the image editor Krita To support Kdenlive financially and contribute to its ongoing development, users have the option to make donations through . Typically, Kdenlive accepts donations in traditional money, but its repository is available on Kivach too as . This way, you can use some of your crypto to support them. \ various channels KDE/Kdenlive Xfce (Desktop Environment) Xfce is a lightweight and open-source desktop environment designed for Unix-like operating systems, known for its efficiency and speed. It was initially released in 1996 by Olivier Fourdan and has since evolved into a mature and user-friendly desktop environment. Xfce provides users with a simple yet customizable interface, making it a popular choice for users who prefer a responsive and resource-efficient desktop environment. Xfce's development is primarily driven by a community of dedicated contributors and developers who work collaboratively to maintain and enhance the software. The Xfce project is known for its commitment to providing a stable and user-focused desktop experience while using fewer system resources compared to more resource-intensive desktop environments. To support the development of Xfce and help its ongoing improvement, users can make donations to the project. and ensuring that Xfce continues to provide a lightweight and efficient desktop environment for users who value performance and customization. Donors can send them funds via Open Collective, which a 15% fee for fiscal hosts. These contributions are essential for covering development costs, infrastructure maintenance, may take Of course, it’s also possible to send them crypto funds via Kivach, without high fees. They appear as . xfce-mirror/xfce4-terminal Tor (Privacy Browser) Well, if you don’t know this one, you likely have been living under a rock. First things first: It’s free and open-source software that enhances online privacy and security by routing internet traffic through a global network of volunteer-operated servers. It was initially developed in the mid-2000s by the United States Naval Research Laboratory and has since evolved into a global community-driven project. no, Tor (short for The Onion Router), isn’t solely to access the Darknet. The Tor network conceals a user's IP address, making it challenging for anyone to trace their online activities, providing anonymity and bypassing online censorship. , a non-profit organization (NGO), leads the development and maintenance of the Tor software and network. The Tor Project To support Tor financially and contribute to its mission of providing online privacy tools for everyone, individuals can make donations to the Tor Project. Their website provides various options for donating, including one-time and recurring donations, as well as options for corporate or institutional support. They accept Bitcoin, Bitcoin Cash, Dash, Dogecoin, Ether, Litecoin, Monero, Stellar, and Zcash. In Kivach, you can find them as . Besides, in case you don’t know, You can activate its use to obscure your transactions just by adjusting the proper switch in the section “Settings (Global Preferences)”. torproject/tor the Obyte wallet is integrated with this privacy browser to protect your personal data. Now, you can explore Kivach and GitHub yourself to support more essential open-source projects. Your cryptocurrency contributions can fuel innovation and ensure these tools remain accessible to all. Do you know any other interesting open-source projects that may need help? Please comment on them below, on our , or via , so we can cover them in future articles for potential donors to know! Telegram channel Discord Featured Vector Image by . Freepik

5 Open-source Projects You Can Support With Kivach — and Cryptocurrencies

5 proyectos de código abierto que puedes respaldar con Kivach y criptomonedas

5 projets open source que vous pouvez soutenir avec Kivach – et les crypto-monnaies

5 ओपन-सोर्स प्रोजेक्ट जिन्हें आप किवाच और क्रिप्टोकरेंसी के साथ समर्थन कर सकते हैं

Kivach と暗号通貨でサポートできる 5 つのオープンソース プロジェクト

5 projetos de código aberto que você pode apoiar com Kivach – e criptomoedas

5 dự án nguồn mở bạn có thể hỗ trợ với Kivach — và tiền điện tử

您可以使用 Kivach 和加密货币支持的 5 个开源项目

Fine-tuning is now available for one of the key models offered by OpenAI. Up to this point, we were only able to fine-tune older model variants with performance subpar to . Maximizing the performance of OpenAI's models without draining your budget is now achievable. the likes of GPT-3.5 and GPT-4 Why fine-tune? Better responses Training with more examples than in few-shot-learning approaches (giving a few examples in the prompt) Shorter prompts - lower costs and latency OpenAI also lists the following benefits: improved steerability, reliable output formatting, and custom tone. You can find all of the code from this article on GitHub: . The code is experimental and several-use-only; don't expect it to be polished. link Please remember that for JSON output, it may be better to use function-calling functionality. That said, this tutorial should show you how to fine-tune in general. Sample use case: JSON output formatting for fake identity generation Using large language models for tasks like JSON output formatting often results in lengthy and costly prompts. Let's explore this challenge with a sample use case. I am a big fan of using large language models (LLMs) like GPT-4 for language processing. Many people use the popular library Langchain for this use case ( ), while others use native function calling features ( ). Both of these use additional tokens and are error-prone. and I wrote about it I made a short demo Let's look at a particular example. Let's assume we often need to generate people's identities in structured formats to seed our demo databases, populate dashboards at development stages, etc. Let's take the Twitter/X user profile and try to generate its parts. {
    "name": "John Doe",
    "handle": "jdoe",
    "age": 30,
    "hobbies": ["programming", "gaming", "reading"],
    "email": "john.doe@gmail.com",
    "bio": "Avid Python programmer and gamer",
    "location": "USA",
    "is_blue_badge": True,
    "joined": "2019-01-01",
    "gender": "male",
    "appearance": "white, brown hair, brown eyes, 6'0",
    "avatar_prompt": "A photorealistic image of a man, white, brown hair, brown eyes, against a blurred backdrop od a home scenery. Use a Hasselblad camera with a 85mm lens at F 1.2 aperture setting and soft sunlight falling on the subject to capture the subject’s creativity.",
    "banner_prompt": "High resolution photo of a desk with a laptop, a gamepad and a book. Canon DSLR."
} The prompt to achieve that with a high degree of success is very long, especially using Langchain templates. Have a look: That is 923 tokens for the input, and the output takes 236. Generating a thousand would cost us $41.85 with GPT-4. With GPT 3.5, we could do it for $1.85. If the promise of fine-tuning can be met and we get performance closer to GPT-4 with shorter prompts, we will save tons of money. Most of the use cases require more data. What we can try to do is to reduce the prompt by fine-tuning to the following: As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt. Generate details of a random Twitter profile. With this prompt and fine-tuned model, we would pay $4.388. 10x less than GPT-4 but almost 3x GPT-3.5. The fine-running costs in this tutorial amount to around $0.4. Let's see how this works out. I have no automatic way of comparing the quality of the generated results, but if you know of any research, please let everyone know in the comments. The code to generate this prompt can be found in the project repository. Preparing the synthetic training data Make sure you have the latest version of the by running . OpenAI package pip install -U -r requirements.txt You also need to include your OpenAPI key in the environment variable. . export OPENAI_API_KEY="sk-XXXXX" Let's use GPT-4 to prepare 50 examples as per minimum OpenAI requirements. It will cost us around $2.4. We're leveraging the power of GPT-4 for high-quality examples to train our model. import openai
import json

prompt = "COMPLICATED LONG PROMPT"

SAMPLE_COUNT = 50

examples = []

for i in range(SAMPLE_COUNT):
    chat_completion = openai.ChatCompletion.create(
        model="gpt-4", messages=[{"role": "user", "content": prompt}]
    )
    print(chat_completion.choices[0].message.content)
    examples.append(json.loads(chat_completion.choices[0].message.content))

with open("training_examples.json", "w") as outfile:
    outfile.write(json.dumps(examples)) Now, armed with 50 strong examples from GPT-4, we can fine-tune our 3.5 model. Data formatting OpenAI suggests using the system message for the input data. It uses a system prompt as a recommended way of passing general instructions. Let's construct our template message. {
    "messages": [
        {
            "role": "system",
            "content": "As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt."
        },
        {
            "role": "user",
            "content": "Generate details of a random Twitter profile."
        },
        {
            "role": "assistant",
            "content": f"{profile_details}"
} We also need to prepare a file with each JSON object in a new line and run it through a . validator provided by OpenAI transform_data.py import json

# Load the data from the json file
with open('training_examples.json', 'r') as f:
    profiles = json.load(f)

# Output file to save the formatted messages
with open('mydata.jsonl', 'w') as out_file:
    for profile in profiles:
        profile_details = json.dumps(profile)

        # Create the desired format
        formatted_message = {
            "messages": [
                {
                    "role": "system",
                    "content": "As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt."
                },
                {
                    "role": "user",
                    "content": "Generate details of a random Twitter profile."
                },
                {
                    "role": "assistant",
                    "content": profile_details
                }
            ]
        }

        # Write the formatted message to the output file, each on a new line
        out_file.write(json.dumps(formatted_message) + "\n") Now, let's run the formatting script (in the repository called . openai_formatting.py python openai_formatting.py You should get the following message. 0 examples may be over the 4096 token limit, they will be truncated during fine-tuning
Dataset has ~14194 tokens that will be charged for during training
By default, you'll train for 3 epochs on this dataset
By default, you'll be charged for ~42582 tokens
See pricing page to estimate total costs In our case, fine-tuning will cost $0.34. Fine-tuning the model I have compiled all the necessary calls into one file. The script uploads the file with our data, waits for it to process, and then starts the finetuning process. Be careful; running it will incur costs! finetune.py import os
import openai
import time

openai.api_key = os.getenv("OPENAI_API_KEY")

file_upload = openai.File.create(file=open("mydata.jsonl", "rb"), purpose="fine-tune")
print("Uploaded file id", file_upload.id)

while True:
    print("Waiting for file to process...")
    file_handle = openai.File.retrieve(id=file_upload.id)
    if len(file_handle) and file_handle.status == "processed":
        print("File processed")
        break
    time.sleep(3)


job = openai.FineTuningJob.create(training_file=file_upload.id, model="gpt-3.5-turbo")

while True:
    print("Waiting for fine-tuning to complete...")
    job_handle = openai.FineTuningJob.retrieve(id=job.id)
    if job_handle.status == "succeeded":
        print("Fine-tuning complete")
        print("Fine-tuned model info", job_handle)
        print("Model id", job_handle.fine_tuned_model)
        break
    time.sleep(3) Run it by typing . python finetune.py If you don't want to wait, stop the script and wait to receive an email from OpenAI. Both the message in the terminal and the email will include the model ID! Now, let's test it! Testing the model Let's prepare the test file. Replace model_id with yours. run_model.py import os
import openai

openai.api_key = os.getenv("OPENAI_API_KEY")

model_id = "ft:gpt-3.5-turbo:my-org:custom_suffix:id"

completion = openai.ChatCompletion.create(
    model=model_id,
    messages=[
        {
            "role": "system",
            "content": "As a response, provide the following fields in a JSON dict: name, handle, age, hobbies, email, bio, location, is_blue_badge, joined, gender, appearance, avatar_prompt, and banner_prompt.",
        },
        {"role": "user", "content": "Generate details of a random Twitter profile."},
    ],
)

print(completion.choices[0].message) python run_model.py And we should receive an output similar to this! {
    "name": "Daniela Kolarova",
    "handle": "PragueReveries",
    "age": 29,
    "hobbies": ["classical piano", "literature", "yoga"],
    "email": "daniela.kolarova@czmail.cz",
    "bio": "Finding harmony through keys, books, and breaths. Embracing Prague's spellbinding tales.",
    "location": "Prague, Czech Republic",
    "is_blue_badge": True,
    "joined": "2014-05-01",
    "gender": "female",
    "appearance": "Caucasian, long wavy auburn hair, green eyes, 5'6\"",
    "avatar_prompt": "Photorealistic image of a caucasian woman with green eyes, playing a grand piano. Use Olympus PEN-F with a 38mm lens.",
    "banner_prompt": "High-resolution depiction of Prague's rooftops, cozy libraries, and serene yoga studios. Samsung Galaxy S20 II.",
} As you can see, we've achieved our goal of generating high-quality data fitting complex instructions with shorter prompts. We didn't measure the quality, so make sure in your use case, this makes sense and is cost-effective. Conclusion Fine-tuning has opened up an avenue to achieve more specific and consistent outputs from OpenAI's models. As demonstrated with the Twitter profile generation example, fine-tuning meets the promise of achieving specific outputs with short prompts. While fine-tuning offers precision, it demands carefully crafted training data to ensure the model doesn't just memorize examples. This process involves initial investments in terms of time and money (luckily, we can generate fine-tuning data with more capable models). Moreover, the quality of outputs should be continuously assessed to ensure they meet the required standards. For businesses or projects that rely heavily on the performance of LLMs like GPT-4, fine-tuning presents a viable option to optimize performance and cost. As with any technology, it's crucial to stay updated with the best practices and latest developments in the field. OpenAI continues to evolve its offering, and adopting a flexible approach ensures that you can leverage the best capabilities of these models for your specific needs. You can find the code for this tutorial on GitHub: . link Subscribe to my profile by filling in your email address on the left, and be up-to-date with my articles! Don't forget to follow me on Twitter @ and subscribe to my blog for more tips and insights! horosin_ newsletter If you don't have Twitter, you can also follow me on . LinkedIn Also published . here

Fine-Tuning GPT-3.5: A Practical Python Example

To keep everyone safe and healthy, the decision to start working from home came to our management team within minutes. I remember the day SupportYourApp decided to switch to the WFH mode. The Covid-19 pandemic was starting to pick up steam, and businesses around the globe were going remote by the dozen every day. Since then, SupportYourApp grew from 500 people to 1200+ professionals who work from all around the world. Fully working from one office is not an option for all members of our team. Yet, global businesses have started a battle to return their employees to their offices. — the company’s CEO said he expected to see all 60 thousand Goldman Sachs' employees back at the office. “I do think for a business like ours which is an innovative, collaborative apprenticeship culture, (remote working) is not ideal for us, and it’s not a new normal,”. So far, only 10 thousand people have returned to their desks. Goldman Sachs — Netflix’s CEO says working remotely is not good for collaboration and is, in his opinion, a ‘pure negative’. Netflix — for almost a year, Google has been trying to incentivize its workers to . The employees were promised free food and other perks that would make office hours even more comfortable . When this motivation failed, the company’s Chief People Officer, Fiona Cicconi, said non-appearance in the office for three days a week will influence their performance review. Google come back to the office than they already were — Salesforce decided to go the other way and said the company would donate $10 to charity per each day an employee will show up to the office between June 12 and June 23. Salesforce What is businesses’ pro-office motivation? Productivity It is widely thought that a team member who works from home spends most of their time not working, watching Netflix, walking around, and only pretending to be productive. This issue can be resolved simply — make sure every team member sends their manager a productivity report at the end of every day, and start utilizing collaboration and progress tools like Asana or Trello. In general, the notion that people are less productive when they work from home is incorrect, as of workers say they are more productive when working remotely. 30% also report doing more work in less time, and 24% say they do more work in the same amount of time. 77% Control As leaders and managers, we want to make sure we can control and monitor the way our teams perform. We want to know what stage every project is on at almost any given moment, and we want to be sure everyone is doing what they are supposed to. We have to remember — micromanagement is not a good approach to management, especially with a growing team. For any C-suite leader, it is better to delegate some leadership tasks to other management members and focus on strategic goals and tasks. Can control really ensure a superb team performance? Not really. Through my tenure as a CEO, I tried several approaches to team management. At the beginning, I tried to be a friend to everyone on my team. That didn’t work, and I soon adopted a dictatorial style — I wanted to know everything that was happening at SupportYourApp, and I was trying to be strict with everyone. Did my team’s productivity improve? It was already good, and I cannot say that anyone’s strict control would make any difference, no matter whether my team works in our offices or remotely. Collaboration & Communication How can a leader ensure collaboration? There are several steps to doing that: Handpick every member of the team to ensure everyone is a perfect fit. Adopt collaboration software like Trello, Microsoft Teams, Slack, Kolab, and so on. Ensure regular communication both inside and outside the office. Encourage brainstorming sessions to make sure everyone’s free to share their ideas. As a manager, trust your team and listen to their ideas — this will not only ensure collaboration, but will actually vitalize creativity. Can an office encourage collaboration? When you have a question, it is easier to just turn your head and ask a teammate for help. But let’s be honest — businesses around the world have been in a remote mode for more than 3 years. We have online communication and collaboration all set up. It is especially true for international teams that cannot gather in one space on a regular basis, or even ever. Pro-office motivation: does it work? Measures taken by Google, Salesforce, Netflix, and many other companies show — most teams are not keen to come back to their offices even for a hybrid schedule. They want to have the possibility to choose where to work and when to come back and work with their teams face-to-face. With that said, will the office culture survive in the post-pandemic world? It will. The office will evolve and become a hub where colleagues can meet, work on projects that require top security measures, and feel their teams having their backs. The main task for a leader is to find a proper approach and proper encouragement. So, as always in the modern world, everything is about balance.

Pro-Office Motivation: Does it Actually Work?

প্রো-অফিস প্রেরণা: এটি আসলে কাজ করে?

Pro-Office-Motivation: Funktioniert das tatsächlich?

Motivación a favor de la oficina: ¿realmente funciona?

Motivation Pro-Office : ça marche vraiment ?

प्रो-ऑफिस प्रेरणा: क्या यह वास्तव में काम करता है?

プロオフィスのモチベーション: それは実際に機能しますか?

친사무실 동기 부여: 실제로 효과가 있나요?

Motivação Pro-Office: Funciona mesmo?

Ofis Profesyoneli Motivasyonu: Gerçekten Çalışıyor mu?

Động lực Pro-Office: Nó có thực sự hiệu quả không?

亲办公室动机：真的有效吗？

Letters. Personal Records. Dated Notes.

is a lightweight and type-safe library to seamlessly create custom database repositories for applications. It provides developers with some built-in CRUD operations, enabling them to focus on adding their own operations, and ensures a clean separation between persistence and domain logic. Despite being database technology agnostic by nature, it currently includes an implementation for MongoDB. node-abstract-repository Node.js Note This article introduces , but it does not include all of its details. You may find the full documentation and some usage examples at , including an example of how to use this library in a NestJS-based application. node-abstract-repository this GitHub repository Why Build Yet Another Repository Library Joining made me switch my gears and start to develop JS/TS-based web applications. My very first assignment was connecting a small backend NestJS app with a database. We had big plans for our app and we soon realized that the domain model owned by my team was going to grow in complexity, and quickly. Furthermore, we saw that this was also the reality in other teams that wanted to use the same kind of solution. ClimatePartner MongoDB All considered, we decided to incorporate a database access utility that implements the to cleanly decouple persistence from domain logic while keeping query logic duplication to the bare minimum. We also wanted it to be of nature so that we could reuse the database access logic that is common to all custom repositories (i.e., CRUD operations over any persistent domain object). Finally, we needed it to implement the to support subtyping-based domain models. Repository pattern abstract Polymorphic pattern So, we started researching the state-of-the-art and discovered several libraries that could fit our requirements. The best candidates we were able to find were and . Mongoose is a well-known Node.js library for MongoDB that implements the Data Mapper pattern and lets developers define schemas to constrain the data models associated with their domain objects. Mongoose, Typegoose, TypeORM However, Mongoose works with concrete data models, which is a complex domain model scenario that results in query logic duplication. Typegoose is a type-safe Mongoose wrapper that allows schema constraint declaration at the domain object field level via JS decorators. Unfortunately, those very decorators leak persistence logic into the domain model. Besides, Typegoose also implements the Data Mapper pattern, thus sharing the same drawbacks of Mongoose. TypeORM, on another hand, implements the Repository pattern and provides some basic support for MongoDB. However, TypeORM presents several limitations compared to Mongoose. Although none of the existing alternatives were exactly fitting our needs, we saw value on Mongoose's solid, well-documented, and complete set of features. On the top of that, we wanted the most lightweight solution possible. That's why we decided to build . node-abstract-repository Cut to the Chase Say we have a domain model that specifies as the supertype domain object and and as subtypes. Here is one possible definition for that domain model: Book PaperBook AudioBook class Book implements Entity {
  readonly id?: string;
  readonly title: string;
  readonly description: string;
  readonly isbn: string;

  constructor(book: {
    id?: string;
    title: string;
    description: string;
    isbn: string;
  }) {
    this.id = book.id;
    this.title = book.title;
    this.description = book.description;
    this.isbn = book.isbn;
  }
}

class PaperBook extends Book {
  readonly edition: number;

  constructor(paperBook: {
    id?: string;
    title: string;
    description: string;
    isbn: string;
    edition: number;
  }) {
    super(paperBook);
    this.edition = paperBook.edition;
  }
}

class AudioBook extends Book {
  readonly hostingPlatforms: string[];
  readonly format?: string;

  constructor(audioBook: {
    id?: string;
    title: string;
    description: string;
    isbn: string;
    hostingPlatforms: string[];
  }) {
    super(audioBook);
    this.hostingPlatforms = audioBook.hostingPlatforms;
  }
} Now, you want to be able to persist and retrieve instances of and any of its subtypes from a MongoDB database. is a custom repository that specifies -related database operations. Here is its definition: Book MongooseBookRepository Book class MongooseBookRepository
  extends MongooseRepository<Book>
  implements BookRepository
{
  constructor() {
    super({
      Default: { type: Book, schema: BookSchema },
      PaperBook: { type: PaperBook, schema: PaperBookSchema },
      AudioBook: { type: AudioBook, schema: AudioBookSchema },
    });
  }

  async findByIsbn<T extends Book>(isbn: string): Promise<Optional<T>> {
    if (!isbn)
      throw new IllegalArgumentException('The given ISBN must be valid');
    return this.entityModel
      .findOne({ isbn: isbn })
      .exec()
      .then((book) => Optional.ofNullable(this.instantiateFrom(book) as T));
  }
} Voilà! inherits a series of CRUD database operations from and adds its own i.e., . Now you can simply instantiate and execute any of the database operations as follows: MongooseBookRepository MongooseRepository findByIsbn MongooseBookRepository const bookRepository = new MongooseBookRepository();
const books: Book[] = bookRepository.findAll(); No more leaking of persistence logic into your domain/application logic! Some Important Implementation Details You may be wondering about certain elements exposed in the previous example. Starting from the top part of the definition, the first of these is . This is one of the two main elements exposed at : a generic template that implements several common CRUD database operations. Furthermore, this class also handles the creation of a Mongoose data model capable of handling subtyping-based book data objects. All this complexity is hidden from you; all you need to know is that you have at your disposal to implement your own database operations, as shown at . MongooseBookRepository MongooseRepository<Book> node-abstract-repository entityModel findByIsbn The only extra effort that is required from you is that you define a map that specifies the types that compose your domain model and their related Mongoose schemas, as specified at the constructor of . It is also important to note that the key of the entry that specifies your domain object supertype must be named , and the key of each other entry must be named after the type name of the subtype domain object it refers to. This is a naming convention required by the inner implementation details of . If you do not have any domain object subtype in your domain model then simply instantiate a map with a unique entry that specifies a key and the type-schema values of your domain object. MongooseBookRepository Default MongooseRepository Default Another element that may catch your eye is . This is an optional interface that extends , the second main element exposed at : a database technology agnostic generic interface that specifies all the supported CRUD database operations to be implemented by any repository. The following snippet shows this relation between these two interfaces: BookRepository Repository node-abstract-repository interface BookRepository extends Repository<Book> {
  findByIsbn: <T extends Book>(isbn: string) => Promise<Optional<T>>;
} Handling instances of interface types instead of classes is a good practice in object-oriented applications; makes your code scalable and better suited to change. Therefore, I would highly recommend that you define your own repository interfaces, or in the case, you are only interested in exposing CRUD operations, instantiate your custom repositories as objects of type , where is your domain object supertype. depending on abstractions instead of implementations Repository<T> T On another hand, implements an interface called . This interface models any persistent domain object type. The interface defines an optional field. The optional nature of the field is due to the fact that its value is internally set by Mongoose. If you do not want your domain model to include this dependency, though, you can just ensure that your domain objects specify an field. And there is nothing wrong doing that, as is the canonical primary key in MongoDB documents. Book Entity id id?: string id Finally, many database operations return objects of type . This type is inspired in the type. Its purpose is to model the concept of "no result". This type is an excellent alternative to returning objects or throwing an exception. The usage of is safer and clearer than having to specify as result type or having to handle an exception that does not represent an application exceptional condition. So yes, this the feature that makes a bit opinionated, but I believe that is worth it. Optional Java Optional null Optional T | null node-abstract-repository Conclusion The library provides the means to  create custom repositories for Node.js-based applications in a fast and easy manner. It is conceived to achieve effective decoupling between persistence and domain logic. Its current implementation is a Mongoose wrapper that includes all the boilerplate code required to perform common CRUD operations over polymorphic domain objects in MongoDB. Thus, developers can focus in writing domain-specific database operations at custom repositories. node-abstract-repository Moreover, the library has been designed to allow developers use many interesting Mongoose features (e.g., creation and validation of polymorphic models as well as hook implementations, just two mention two) without having to deal with most of Mongoose's inner complexity. Also published . here Lead photo by on Unsplash Jan Antonin Kolar

Building a Scalable Node Abstract Repository for MongoDB

There are annual seasonal changes in the human organism

And say goodbye to keyword-based search While GPT 3+ or ChatGPT, prompt engineering is easier to understand intuitively. With many guides and examples available on the web, and social media. Such as OpenAI best practices to prompt engineering List of ChatGPT prompts Embeddings, require programming, and are less understood, due to various counter intuitive behaviour on how it works. But, is an extremely powerful tool for search, or to be used together with existing text-based models, for various other possible use cases. Embeddings are arguably an equally powerful tool, within the AI toolkit, for instruction models. Due to its ability to handle searches across different words and sentences, or even entire languages. Focusing on searching for the relevant document, for any query. For example, it can be used to power searching and answer from an English-based documentation. In English ... Or Japanese ... Or any other languages that the AI model supports. Vector embedding can be used for search, or other tasks such as question-answering, text classification, and generating text. Note that this article focuses on the search aspect, the answering process is in a follow-up article. What is a vector embedding? To generate a vector embedding, one will use an embedding AI model, which converts any text (a large document, a sentence, or even a word), into an "N dimension array", called a vector. For example a sentence like How do I write a UI test script with Uilicious? Can be converted into an array (called a vector) via : OpenAI text-embedding-ada-002 model [0.010046141, -0.009800113, 0.014761676, -0.022538893, ... an a 1000+ numbers] This vector represents the AI model's summarized understanding of the text. This can be thought of as an "N-word summary" written in a language that only the AI can understand. Where related documents will have a close distance from each other, based on the AI's understanding of the document (and not just its text). This is a major leap beyond the simple keyword searches of classic search engines, as it can handle variations in sentence structure and language (provided the AI model is trained to understand said language). Take the following as a hypothetical example, oversimplified inaccurately into 2 dimension space so that it is easier to understand: Which can be visually presented as the following in 2D space. For example, D1,2,3 are all documents related to how to use Uilicious in various ways and are grouped together in one cluster D4 and D5, being simply links and having no inherent value beyond that, are grouped separately in another cluster. Furthermore, D1 & D2 are further grouped together, as they are about Uilicious testing commands, using our very own JavaScript-based testing language. While D3 is grouped separately, as it is regarding using the web driver protocol on our infrastructure directly, which is intended for a different use case and audiences. Similarly, for Q1 and Q2, despite the drastic differences in sentence structure and language, because it is essentially the same question, the two questions are grouped together. Additionally, while the question could technically be interpreted both ways (using Uilicious test script, or webdriver protocol), because the question implies the usage of Uilicious test scripting over webdriver, its location is "closer" to D1 & D2, and further away from D3. As such, despite having huge overlaps in keywords, these nuances in groupings are captured by the AI encoded within the embeddings. Highlighting its distinctive difference to keyword search In reality, however, instead of an oversimplified 2 dimension array which is easy for humans to understand, an embedding can easily be a 1,000+ dimension array. This array is unique to the specific AI model used, and cannot be mixed with another AI model's embeddings. Math notes: N-dimension math is not compatible with 2/3D math While the oversimplified 2 dimension examples, are good for understanding the high-level concept of grouping relatively to one question (or one point of view), it does not accurately represent an N-dimensions. Due to complicated N dimension math, you can have situations, where A can be close to B, B can be close to C, but A and C can be considered far from each other. Which is an extremely counter-intuitive gotcha. Such distances are only useful when used relative to the same point, and the formulas used. Which can be calculated either using also known as Pythagorean Theorem on steroids, it is the most common distance metric used and is the straight line distance between two points in N-sphere. : Euclidean distance it is a measure of angular distance between two points in an N-sphere, and is useful for measuring the similarity of documents or other vectors. : Cosine Similarity these two metrics are used to measure the differences between two vectors, and are useful for measuring the "edit distance" between two strings. Manhattan or Hamming Distance: While the effectiveness of each formula has their respective pros and cons, for different use cases. For textual search, it is generally accepted that Euclidean distance "works better" in most cases, and "good enough" for cases where other methods edge out. All of which, is used in effect to reduce N-Dimensions, to a single dimension (distance), relative to a single point. This as a result, would mean groupings can / may change drastically depending on the question asked. This "relativity" nature of distances, makes classic database search indexes ineffective. If that makes no sense, this is how 4 dimension space is visualized properly with math N-Spheres. Now imagine 1,000 dimensions? Yea it makes no sense. So without derailing this topic with a PHD paper, I will summarise this as just trusting the math professors. All we need to understand is that in general, the closer the distance is between two vector embedding points, the increased likelihood they are relevant to each other. From a practical implementation standpoint. Start with using Euclidean distance first. Before considering using the other formulas which are fine-tuned for better results through trial and error for your use case (not recommended). Searching embeddings with a vector database So given that we can convert various documents into embeddings, we can now store in within a database and perform a search with it. However, unlike an SQL database searching with text, both the search and the data being searched is the vector embedding itself. This means that traditional database search indexes are ineffective when it comes to searching for embeddings. We can have all your documents embeddings, precomputed, and stored into a vector search database. Which can then be used to provide a list of matches, ranked by the closest distance. This can be done using existing vector databases such as : a popular open-source database that can be used to store vector embeddings and search them efficiently. REDIS : a library created by Spotify which uses an optimized algorithm to search embeddings quickly. Annoy : a library created by Facebook which provides efficient search algorithms for large datasets. FAISS One major thing to note, vector search "database tech" is relatively new. Where a large majority of the vector search databases were designed for use cases found in companies like Facebook, Spotify or Google, with record sets in the size of millions or billions. And may not be optimised for small datasets. This is going to be a constantly changing field in the next few years, here is a github 'awesome-list' to help track and find future vector search databases As such, in general, we found for small datasets of (<10,000 ~ 100,000 embeddings), keeping the embedding dataset in memory and brute-forcing euclidean-distance-squared is "good enough" for many use cases, and will sometime outperform formal database solutions (which will have disk/network overheads) with something like the following. The obvious downside to this approach is that the entire dataset must be small enough to fit into memory without the overhead. Regardless if you are using local in-memory embedding search, or a formal vector search database. That's it! Embedding search is just a sort and rank algorithm that works flexibly with various languages, and scenarios. The question for you as the reader is how you can use it. It can be used as it is as a possible google search replacement, or together with other tools, from chat, to games. The possibilities are endless and open to exploration. ~ Until next time 🖖 live long and prosper Eugene Cheah @ tech-talk-cto.com Originally posted on: https://substack.tech-talk-cto.com/p/introducing-ai-embeddings-and-how All Images used, with their proper attribution by on Man in magnifying glass Marten Newhall Unsplash Zach Galifianakis Math meme by on File drawers Jan Antonin Kolar Unsplash by on Dream big wallpaper Randy Tarampi Unsplash

Understanding Vector Embeddings for AI-Powered Search

এআই-চালিত অনুসন্ধানের জন্য ভেক্টর এম্বেডিং বোঝা

Vektoreinbettungen für die KI-gestützte Suche verstehen

Comprender las incrustaciones de vectores para la búsqueda impulsada por IA

Comprendre les vecteurs incorporés pour la recherche basée sur l'IA

एआई-पावर्ड सर्च के लिए वेक्टर एंबेडिंग को समझना

AI を利用した検索のベクトル埋め込みについて

AI 기반 검색을 위한 벡터 임베딩 이해

Compreendendo incorporações de vetores para pesquisa com tecnologia de IA

Yapay Zeka Destekli Arama için Vektör Yerleştirmelerini Anlamak

Hiểu các nhúng Vector cho tìm kiếm do AI cung cấp

了解用于人工智能搜索的向量嵌入

The Internet is a mirror of the collective human psyche, and it’s nothing if not downright chaotic. Just like the people that give it life, the internet is an imperfect entity rife with the propensity for good or downright terrible. However, just as light banishes darkness, we hope that the good and reasonable initiatives on the world wide web continue to thrive. This year, Noonies’ Award Category, presented by ,  shines a light on the thinkers, builders, and of course, users that ensure that the gift of the internet keeps on giving. Internet Heroes HackerNoon Writing Contests Here are the stats: 4,743 nominees. 371 HackerNoon awards for 2022 Across 5 award categories: Web3, Emerging Tech, Gaming, Internet Heroes, and Programming. And a monumental 143,156 votes cast over at noonies.tech To see the winners simply visit , pick an award, and discover which name appears at the top. That’s the winner! noonies.tech The category alone is announcing 100 winners this year. Let’s congratulate them all! Internet Heroes HackerNoon Contributor of the year - CYBER SECURITY AWARENESS With 1,891 votes, Cloud Security Engineer and Cybersecurity , smashed this category. Engr Naina Emmanuel HackerNoon Contributor of the year - MANAGEMENT an International recruitment agency, won this category by writing about lessons and laws in different management styles. Alcor, HackerNoon Contributor of the Year- SEO Sleuth SEO is the spice of the Internet and, is the spice master. Manfye Goh HackerNoon Contributor of the Year- EDUCATION From the origins of decentralized finance to what the metaverse will look like in a few years, taught us a lot in 2022. Mickey Maler HackerNoon Contributor of the Year- All About Teamwork , founder at Adadot.com, the world’s first fitness tracker for work won, this round. Alex Harris HackerNoon Contributor of the Year- LEARNING For sharing her learning journey and garnering 637 votes, won this category. Shloka Shah HackerNoon Contributor of the Year- Most Valuable Marketer , Head of Product Marketing at Livecycle gets the trophy for this one. Zevi Reinitz HackerNoon Contributor of the Year- BUSINESS-STRATEGY Marketing, Product Guy & Writer, brought high-value content, such as his which is probably why he got 549 votes to win this category. Kolapo Imam interview with Google Product Marketing Manager Vincent Xu HackerNoon Contributor of the Year- CAREER-DEVELOPMENT And the winner of this category is serial entrepreneur . Kirill Manaenko HackerNoon Contributor of the Year- FACEBOOK NFT and Web3 guru wins this category. Tigerchops HackerNoon Contributor of the Year- INTERNET is the winner in this category. Ewere HackerNoon Contributor of the Year- SOCIAL-MEDIA Congratulations to the head of Admitad ConvertSocial ! Ksana Liapkova HackerNoon Contributor of the Year- ONLINE-EDUCATION won this category, a step further in reaching her goal of educating 100-out-of-school children in Nigeria using music, literacy, and technology. Celine Aju HackerNoon Contributor of the Year- JOBS CEO of SIDUSHEROES.COM won this category. Congratulations! Dan Khomenko HackerNoon Contributor of the Year- CLIMATE-CHANGE Certified Zero Waste professional and Co-founder BreatheIO won this category. Sana Nauman Chaudhry HackerNoon Contributor of the Year- BUSINESS-GROWTH After smashing the BUSINESS STRATEGY category, won the BUSINESS-GROWTH category too. Kolapo Imam HackerNoon Contributor of the Year- PSYCHOLOGY Congrats to , a Backend Developer with Coding and Philosophy as main interests. Leela Krishna Kumarz HackerNoon Contributor of the Year- CYBER-THREATS Cyber threats are not to be taken likely and cybersecurity writer Nduka knows why! John HackerNoon Contributor of the Year- HIRING Software Engineer won this category. Andrei Molchanov The Greatest Storyteller is officially the greatest storyteller of 2022. Zevi Reinitz HackerNoon Contributor of the Year- DESIGN , thank you for your amazing stories. Sergey Golitsyn Super Career Strategist of 2022 And the award goes to a Software Engineer with impeccable writing. Andrei Molchanov HackerNoon Contributor of the Year- GROWTH-HACKING bags his third award for the year! Kolapo Imam HackerNoon Contributor of the Year- INVESTING Besides teaching about investment, stories are fun to read. Congratulations! David O’s HackerNoon Contributor of the Year- DATA-SECURITY creates content to make the web a better place! Zell Liew Critical Thinker of the Year Eight-Time "Noonies" Award Winner, wins again! Nebojsa ”Nesha” Todorovic HackerNoon Contributor of the Year- BOOKS Congratulations to , one of the world's leading consumer product industry experts. Keep up the good work. Branden HackerNoon Contributor of the Year- GROWTH Congratulations to , a software engineer writing about how we can all keep growing professionally and personally. Andrei Molchanov HackerNoon Contributor of the Year- ART is a Senior Advisor, General Counsel, New Pavilion, Senior Counselor, American Blockchain PAC associate AND a HackerNoon Contributor of the Year in Art! Ralph Benko HackerNoon Contributor of the Year- JOB-HUNTING shares the latest trends in hiring and workplace culture at some of the largest tech companies. Rick Chen HackerNoon Contributor of the Year- MOTIVATION is a Backend Developer with Coding and Philosophy as his main interests. Leela Krishna Kumar HackerNoon Contributor of the Year- PRODUCT-MANAGEMENT Congratulations to . Kolapo Imam HackerNoon Contributor of the Year- PHILOSOPHY Congratulations for winning his second award! Ralph Benko HackerNoon Contributor of the Year- COMPANY-CULTURE shares the latest trends in hiring and workplace culture at some of the largest tech companies and wins the HackerNoon Contributor of the Year in Company Culture award. Rick Chen HackerNoon Contributor of the Year- ELON-MUSK , an award-winning writer & guerrilla marketer wins another award! Ghost of HackerNoon HackerNoon Contributor of the Year- BOTS Congratulations to , a Senior Python Developer. Maksim Kuznetsov HackerNoon Contributor of the Year- BEST-PRACTICES Congratulations to , a Senior Ruby on Rails Developer Alexey Shepelev HackerNoon Contributor of the Year- DEVELOPER Congratulations to , a software tester. Sergei Shaikin HackerNoon Contributor of the Year- LEADERSHIP is the example of a leader herself! She has focus in User Acquisition & Growth, enjoys running marathons, is a fitness enthusiast and a TEDx Speaker. Annica Lin HackerNoon Contributor of the Year- BEGINNERS-GUIDE Congratulations to , a full-stack web developer, crafter, blogger, cosplayer, fiber artist, yoga teacher, and gamer. Abbey Perini HackerNoon Contributor of the Year- FREELANCING Congratulations to once again! Ghost of HackerNoon Best Productivity Software Everybody's favorite - , is on fire! Notion HackerNoon Contributor of the Year- CUSTOMER-EXPERIENCE Congratulations to , the CEO of SupportYourApp, Co-founder of Label Your Data and Outstaff Your Team! Daria Leshchenko HackerNoon Contributor of the Year- CUSTOMER-SUCCESS Congratulations to for winning second award in a row! Daria Leshchenko HackerNoon Contributor of the Year- WOMEN-IN-TECH Congratulations to for winning the HackerNoon Contributor of the Year on Women in Tech! Annica Lin HackerNoon Contributor of the Year- FOUNDER-INTERVIEW is building digital products at Evrone.com and winning the Noonies! Elizabeth Lvova HackerNoon Contributor of the Year- CYBERCRIME Congratulations to , a Ph.D. Candidate, Blockchain Researcher,  web3 technical writer, developer, and Audio platforms researcher. Olusegun Joel Titus HackerNoon Contributor of the Year- INTERNET-CENSORSHIP is on fire! Ghost of HackerNoon HackerNoon Contributor of the Year- PRODUCTIVITY has read 6000 pages of programming books per year since 2016 and just like that wins the Noonies award! German Tebiev HackerNoon Contributor of the Year- FUNDING Congratulations to , a seasoned blockchain writer interested in crypto education, DAO, NFT, Defi, and Web3. Olayimika Oyebanji Remote Work Warrior is the remote work warrior of the year! Chingiz Nazar HackerNoon Contributor of the Year- PODCAST is building digital products at Evrone.com and smashing this year's Noonies. Elizabeth Lvova HackerNoon Contributor of the Year- MUSIC is a content creator with 20 years of experience and over 5 million views who writes about Content Creation, Self Help & Business. Jesse Young El Best Online Lecturer Please welcome , the best online lecturer! Abdul Bari Patron Saint of Privacy is our Patron Saint of Privacy this year. Avast Secure Browser HackerNoon Contributor of the Year- HACKATHONS Congratulations to ! Alex R HackerNoon Contributor of the Year- BLOGGING Congrats to , well deserved! Erik Emanuelli HackerNoon Contributor of the Year- ADVERTISING is on fire this year and wins her third award! Annica Lin Coolest Chrome Plugin helps remove known paywalled sites from your search results. A free and open internet is just one click away! Free Internet Plugin HackerNoon Contributor of the Year- ENTREPRENEURSHIP is the host of the Success Story Podcast and Founder/CEO of OnMi Patch. Scott D. Clary HackerNoon Contributor of the Year- CREATIVITY wins for his expertise on creativity. Sourav Das HackerNoon Contributor of the Year- SCIENCE-FICTION Congratulations to , well deserved! Axel Best Technology Email Newsletter content on copywriting, marketing & creativity brings him an award this year. ’s Eddie Shleyner HackerNoon Contributor of the Year- CONTENT-STRATEGY is a freelance writer for B2B SaaS. When she's not writing for clients, she's managing her own blog and winning Noonies! Favour Agari HackerNoon Contributor of the Year- COVID19 Congratulations to ! Kyle W. Beach HackerNoon Contributor of the Year- LIFE-LESSONS Congratulations to , a web developer writing essays about mindset, productivity, tech, and others. Roxana Murariu HackerNoon Contributor of the Year- MENTAL-HEALTH is a six-figure freelancer and strategic advisor who has helped companies secure more than $500 million. Matthew Proffitt HackerNoon Contributor of the Year- FOUNDER-ADVICE Congratulations ! Alex Paden Best Social Media Tech Educator is the best social media tech educator! He discusses various software engineering topics with examples and adds fun elements to them. He always tries to teach by example here on this educational Youtube channel which he believes is the right way to learn. Hussein Nasser Tech CEO of the Year is the Tech CEO of 2022! Congratulations! Troy Goode Best Tech Educator on Instagram is a Computer Scientist who likes to engineer things and share them online. Estefannie HackerNoon Contributor of the Year- COPYRIGHT is an artist by trade (acting, music, writing) and a blockchain by necklace.Congratulations! Nile Sarkisian HackerNoon Contributor of the Year- HISTORY If today is going to be a part of history then sure is going to be remembered as a prominent historian in cyberspace who is a cold-brew addict who simplifies Web3 for the curious men and women. Congratulations! Joel Mascarenhas Green Tech Advocate of the Year Congratulations for being the shining example for everyone in the cyberspace on how tech and nature can go hand in hand! He is the founder and CEO of Salesforce.com Mark Benioff HackerNoon Contributor of the Year- DIVERSITY has given the most diversified stories to his readers this year, he is a marketing executive, digital junkie, and pop culture lover. Congratulations! David Deal The Twitter Animal Account That Most Brightens Your Day is the twitter animal account of 2022 that brightened up everyone’s day and improved our spirits throughout the year. Congratulations! 🐕 genius_dogs HackerNoon Contributor of the Year- CULTURE 2022 sure has proved as a man of culture who is also a marketing executive, digital junkie, and pop culture lover. Congratulations! David Deal Best Use of Tech for Democracy While democracy is what keeps us and our rights safe, its quite astonishing how made sure to keep the very foundation of it out of harm's way. He is the founder and CEO of Change.org, the world's largest platform for social change. Ben Rattray HackerNoon Contributor of the Year- MANAGEMENT-AND-LEADERSHIP is an Author and a Former AVP Engineer @Swiggy. Congratulations! Vinita Bansal HackerNoon Contributor of the Year- SALES Congratulations to ! Scott D. Clary HackerNoon Contributor of the Year- ETHICS is the World’s 1st AI-Powered Omni Social Shopping Network, for People, Brands, and Sustainability.Congratulations! Ã€LA.HAUSSE Tech Career Trendsetter is the world's largest professional network on the internet. You can use LinkedIn to find the right job or internship, connect and strengthen professional relationships, and learn the skills you need to succeed in your career. Congratulations! LinkedIn HackerNoon Contributor of the Year- DATA-PROTECTION Data has always been a top tier asset that helps one gain leverage but it also brings the horrors of it being taken from us without our consent, and has been at par with keeping us updated on how to stay protected. Or Hillel HackerNoon Contributor of the Year- FOUNDER-STORIES Congratulations to . Julie Plavnik HackerNoon Contributor of the Year- LAW is the Founder & CEO of ROYBI Robot and a member of the Forbes Technology Council. Congratulations! Elnaz Sarraf HackerNoon Contributor of the Year- SELF-IMPROVEMENT combines ideas from data science, humanities, and social sciences. Congratulations! Nikola O. HackerNoon Contributor of the Year- GOVERNMENT rises with the strength of a thousand generations. Chitose Nakamoto HackerNoon Contributor of the Year- HUMOR It's said the most difficult emotion to crack is humor but has been blessed with comical wittiness. Congratulations! Valerie Ejegi Who is the Real Captain Kirk? Congratulations to . William Shatner - Star Trek: The Original Series Who is the Real Dr. Leonard McCoy? Congratulations to . Karl Urban - Star Trek (Kelvin Timeline) Who is the Real Spock? Congratulations to . Leonard Nimoy - Star Trek: The Original Series HackerNoon Contributor of the Year- PERSONAL-DEVELOPMENT is an author, entrepreneur, and growth advisor. Congratulations! Baptiste Monnet Who is the Real Hikaru Sulu? . Congratulations! George Takei - Star Trek: The Original Series HackerNoon Contributor of the Year- FUNDRAISING In a world that runs on money has the super power to know how to get it. She is the Co-Founder & CEO of Atri Labs - Creating a new full-stack web development framework. Congratulations! Darshita Chaturvedi Most Controversial Tweeter of the Year They say any type of publicity is good publicity and used it quite well but at what cost. JK Rowling HackerNoon Contributor of the Year- MVP Congratulations to , who is a Software Engineer from the Land Down Under. Valerii Udodov HackerNoon Contributor of the Year- NETWORKING is a full-stack computer science engineer and Linux lover who writes about programming. Congratulations! Aitor Alonso HackerNoon Contributor of the Year- PERSONAL-DATA is an SEO & Affiliate Marketer for Finance & Technology. Congratulations! George Tam RICK SANCHEZ OF THE YEAR It would be an understatement to call a brilliantly mad man just like Tony Stark. Congratulations! Elon Musk

#Noonies2022 Awards: The List of Winners in the Internet Heroes Category

Premios #Noonies2022: la lista de ganadores en la categoría Héroes de Internet

#Noonies2022 Awards : la liste des gagnants dans la catégorie Internet Heroes

#Noonies2022 पुरस्कार: इंटरनेट हीरोज श्रेणी में विजेताओं की सूची

#Noonies2022 Awards: インターネットヒーロー部門の受賞者リスト

Prêmios #Noonies2022: a lista de vencedores na categoria Heróis da Internet

#Noonies2022 Awards: Danh sách những người chiến thắng hạng mục Người hùng Internet

#Noonies2022 奖项：互联网英雄类别获奖名单

On Wednesday 23 November, some vice presidents of the European Parliament declared that the official website was under a DDoS attack. Marcel Kolaja on Twitter: “The European Parliament is under a cyber attack. As Quaestor responsible for ICT equipment, I’ve been in touch with the IT department and we will do our best to defend our institution. This happens after the European Parliament declared Russia a state sponsor of terrorism.” The responsable for the cybersecurity of the Parliament, and vice-president, Dita Charanzová stated in a tweet that this “sophisticated” cyber-attack came just after the that declared Russia a state ‘sponsor of terrorism’ after Moskow’s missiles killing civilians in Ukraine. resolution Dita Charanzová writes on twitter: “The EP was the target of a sophisticated cyber attack this afternoon. Just moments after we adopted the resolution on Russia. Pro-Russian hackers have already claimed responsibility for the attack.” There’s also some senior of the EP that wants to remain anonymous, that said: “it might be the most sophisticated attack that the Parliament has known so far.” The DDoS attack consists in sending a lot of traffic to the victim, usually, hackers use a botnet to exponentially increase the number of packets sent to crash the server. Eva Kaili, another vice president of the EU, reported to that they have a strong indication that the hacking team responsible is called Killnet, a pro-Russia organization. Politico She also tweeted some updates about the case: At the moment the attack is ended, but the National Cybersecurity Center based in Belgium confirmed that an investigation is opened at European Level, that’s all they say. Also published . here

European Parliament under Cyberattack after Declaring Russia ‘State Sponsor of Terrorism’

By segmenting your portfolio into several topics, you may build it up by submitting applications to freelance writing job sites. As a freelance writer, you are constantly searching for the ideal writing opportunities. There are numerous Freelance writing websites to help you monetize your skills. Two methods are utilized to locate freelance writing jobs. You must spend money on marketing initiatives like networking and a blog with guest posts. Applying for writing employment as a freelancer is another option. If you have experience, you may have a portfolio with many different instances. However, if you are a novice, things could seem a little scary because many clients need authors with past experience and talents. But you can still try your luck as a beginner on freelance platforms. 17 Best Freelance Writing Job Sites in 2022 Following are the 17 best freelance writing job sites in 2022: 1. Fiverr People and businesses search Fiverr, the world's largest marketplace for digital services, to locate independent contractors with the necessary capabilities. Because it enables you to finish relatively quick, little, one-time jobs that they refer to as "gigs," it is known as a "micro-task" website. On Fiverr, you may offer a wide range of services, from properly skilled Work to odd things like dressing up for funny videos and singing whatever song you want. By opening an account, providing some basic professional details, and setting up payment processing, you may begin working on Fiverr right away. 2. Guru Use Guru if you are a beginner looking to break into the freelance writing industry. Similar to Fiverr, Guru allows you to bid on tens of thousands of writing jobs. The website is free to use but to apply for writing employment; you must first register. After creating your free account, you can sort jobs depending on your choices. Guru.com offers major organizations the chance to manage an even wider range of duties and abilities with its enterprise-level solution. This service tier makes it easier to hire and manage several gurus. 3. Freelancer Like Upwork, Freelancer.com has more than 42 million members from 247 nations. A single dashboard gives you access to a wide range of hidden talent. It's also important to remember that using the website is accessible. Freelancer similarly runs their business as that of Upwork. To later submit applications and make offers, create a profile. Numerous freelancers are requested to apply for a project, allowing firms to choose the most competent candidate. Consequently, building your profile on it could lead to several opportunities for writers with business management expertise. 4. Contena Contena is a top website to visit for freelance writers if you require high-quality content. It is an exclusive platform for managing content, hiring editors, and working with writers. Each freelancer available has undergone extensive screening and testing. The fact that Contena also teaches writing is the best part, though. Additionally, Contena provides an academy where you may improve client management, get new writing clients, and receive more recommendations. It is excellent for seasoned writers looking for reliable clients. If you don't have enough time to look for good gigs, this site will assist you to save time. 5. Upwork The vast tree of vocations offered on the freelance marketplace Upwork includes writing as just one branch. With 18 million other authors and 5 million clients, breaking into the freelance writing business might be challenging. But it's not likely. If you are looking to recruit authors, there are endless opportunities on Upwork. You will have to put some time into selecting the top applicants for your projects. Employee training to meet your level of criteria for inexpensive content will likely take some time. There are no restrictions on joining Upwork in either scenario. The platform offers both short- and long-term contracts. There are also prospects for freelance writing on an hourly and project basis. 6. LinkedIn With millions of users, LinkedIn is still, without a doubt, the biggest professional-focused website in the world. If you still think LinkedIn is solely a job-hunting platform, it's time to update your knowledge. For authors that write for business-to-business journals, it is a sensible choice. It's because many businesses actively post job openings online and seek full- and part-time writers to provide website content. You can get timely and appropriate alerts about your network on LinkedIn's Notifications tab. You can browse account-related activity, content you've published, and connections. 7. Indeed It could be challenging to find contract-based or freelancing Work. Full-time and part-time employment from various businesses is frequently offered on Indeed. Media companies, small businesses, and content creators list or advertise gigs on Indeed. Most of the jobs mentioned here are full-time, so keep that in mind. You can perform a job type and industry search. You can do searches as a content marketer, SEO writer, or content writer. The website is open to everyone and provides many opportunities for writers. It offers a variety of jobs and saves time. Using this website, you can fix the pricing for a specific market or sector. By incorporating your organization's application tracking system (ATS) with Indeed Apply job advertisements, you can decrease the number of candidates. 8. Blogging Pro You can browse through thousands of lucrative writing projects on BloggingPro. It is a superb platform that only caters to independent authors. Although it charges businesses and individuals to post their job openings, authors are free to apply for those roles. Writers can find many opportunities, including: Full-time jobs Part-time jobs Remote employment Freelancing possibilities Information on how to apply for the job will be given to you. For instance, many job posts encourage you to send a customized message to a specific email address. When doing so, be sure to send your best email. The website's best advantage is that you are not obliged to create an account there to send an email. 9. Writers Work Writers Work is a reasonably priced job board that provides open positions for freelance writers in the present. Both exclusive Writers Work jobs, and job postings from other job boards are sources for it. It's an online program or service for writers, particularly independent ones. The writer has access to a single platform where they may view all of the most recent writing job postings from various websites. In contrast to most freelance job boards, Writers Work only focuses on writing jobs, such as creating blog posts, website material, copywriting, and social media posts. Authors can use it as a tool to find the position that best suits them. When a writer has all their tasks in one place, it is simpler to manage. 10. FlexJobs FlexJobs is most frequently used to find freelance writing jobs. The platform serves as a job board where you may look for the appropriate position by entering a term or location in the search area. Additionally, you may create an account, personalize your job search, and let the website pick the ideal job for you. It sounds like the application process for jobs on FlexJobs is not too complicated. It is simple to use and navigate the platform. Employers can conduct the same search for you as job seekers do, and if they discover that you meet their requirements, they can get in touch with you directly. Candidates looking for remote and flexible employment can interact with firms of all sizes through a web-based job board called FlexJobs. 11. MediaBistro Most job postings are for full- or part-time professions, while there are alternatives for contract or freelance Work. It’s essential to so that the work does not put their health on stake. You can focus your job search by using the filtering options. You can choose a premium subscription if you want a better chance of finding Work on MediaBistro. You can get all the crucial client-pitching advice if you buy the premium edition. keep freelance writers slim The best website to look for writing jobs on if media is your area of expertise is MediaBistro. Numerous media organizations are open to to complete their writing tasks. On MediaBistro, some of the significant businesses, including regional newspapers, television stations, and broadcasting, may post job positions. hiring freelance writers 12. iWriter iWriter is devoted to assisting authors in finding employment, unlike other services. It works well for authors of all experience levels. However, remember that its customers have particular requirements and need the greatest writing. You can begin writing as soon as you register with iWriter. This implies that you may be able to begin getting paid for your writing right more quickly. Users actively seek out certain articles on iWriter, eliminating any writing-related conjecture. Simply choose a request, ignore the keywords and particular specifications, and compose the content. 13. Kolabtree Businesses and academic institutions worldwide can hire independent freelancers for short- or medium-term projects through the internet marketplace known as Kolabtree.com. People or enterprises needing Ph.D. competent professionals can publish those projects and invite freelancers to make bids to successfully work on short- or medium-term projects. You were requested to examine your Work after getting the deliverables for a project that you posted. Please be aware that until you get in touch with the expert again and share your viewpoint, your project's cost will be kept in your project's wallet. You can give the money to them if you think the task was successfully completed; alternatively, if your Work requires revisions, you are free to do so. 14. Writer Access Businesses can organize content and employ and manage freelance writers. They can distribute the content they create directly to most platforms due to a robust content platform called WriterAccess. Businesses may rely on the platform to provide them with access to content that enhances their operations. Businesses may spend more time on their most important tasks. Customers can choose from a number of packages to guarantee they always obtain the material they need for managing their enterprises. Through the portal, customers may also get free resources and services. 15. Freelance Writers Den Anyone who wants to start from scratch and create a successful freelance writing profession should consult The Freelance Writers Den. To be a writer, you don't have to be an extrovert or an introvert. Writing is a skill that can be learnt by anyone with proper dedication. By writing more often, you can get better at it. If you want to learn from experts in the freelance writing field, develop a successful business, and avoid having to figure out the writing game on your own, The Writers Den is the perfect place for you. Freelance writers can easily earn a few hundred or a thousand dollars per month. 16. Constant Content Similar to other top content providers, Constant Content pairs independent writers with clients who require blog posts, articles, and different types of content to increase search exposure and brand recognition. Users who register with Constant Content have the option to submit projects and communicate with authors who have a variety of market specialties. Customers can access the content they need from Constant Content in five different ways, not just one or two. The business gives businesses a method to get in touch with knowledgeable independent contractors in a range of fields and specialties. 17. People Per Hour On the micro gig economy website People Per Hour, tens of thousands of different types of freelancers can find Work. Writing assignments are common on People Per Hour because most companies need to persuade customers of their worth. There were intriguing job listings for writers who could translate text on one of the few websites that were accessible. Additionally, it provides incredible opportunities like employment editing and proofreading academic papers. Visit their website and sign up there to work as a freelancer. Next, search for the position you want, such as "freelance writing," and present your qualifications to any company looking for authors. Final Thoughts All the sites mentioned above are best for freelance writers. You can earn enough from the comfort of your home. Just make sure to get a proper understanding of it before starting Work.

17 Best Freelance Writing Job Sites In 2022

How to Handle Asynchronous Data Requests Using Redux Toolkit

In retrospect, the narrative and overly expressive nature of storytelling may not blend with the scientific and mostly straightforward nature of technology. Many may even wonder why they are in the same sentence. However, has proven that consumers crave genuine connections with the brands they patronize and these connections are often fostered  through storytelling. Consumers no longer care for dry data and numbers that make sense to no one but the company’s sales team. research To emphasize , Chip Heath, a professor at Stanford’s Graduate School of Business, had his students make a one-minute pitch to their classmates supporting or opposing the proposition that non-violent crime is a serious problem. While most students used statistics in their pitch, only one in ten incorporated storytelling. After a ten-minute break, he asked the students to write down every argument they heard in those pitches. the power of stories The results were eye-opening. 63% of the students remembered the stories told while only 5% remembered a statistic. Is that enough to convince you that the best way to remain unforgettable as a brand is to tell your story? In case you need more convincing, here are four reasons why your tech brand should worry about storytelling: 1. Stories Simplify A lot of work goes into creating tech products and services:  research, collecting data, engineering, research again, IT tests, prototyping, software development, design, testing again, and whatnot. All these before the product is finally released into the market. Despite all the hard work this usually takes, your customer doesn’t care. Your customer doesn’t care that your technology is fitted with an Intel Core i9-12900K processor or that you store their data in some of the world’s sophisticated data centers in Europe and North America. In this case, all they want to know is that their privacy is your greatest priority and they can use your platform without worrying about having their information sold to the highest bidder. Tech is complex, that much we can agree on. But its primary purpose is ease; to simplify complex processes and solve some problems. The best way to communicate that to your customers is through storytelling — not by making a list of what your technology is made of (no matter how impressive it is). There is no better way to express your most complicated ideas in its most digestible form. 2. Emotions Sell Faster Than Logic Have you ever heard or read this statement somewhere before: “people will forget what you said; people will forget what you did, but people will never forget how you made them feel.” It’s one of ’s greatest quotes. Well, the same applies in marketing. Maya Angelou Many researchers and neuroscientists agree that logic is the least impactful factor when humans make purchasing decisions. Bolstering that assertion is Gerald Zaltman, a professor at Harvard Business School, who noted in his book — “ ” — that 95% of human purchases are done subconsciously. This means that your brand’s success is largely dependent on how much of an emotional connection exists between the brand and the customer. How Customers Think: Essential Insights into the Mind of the Market But then, how do you evoke emotions? have shown that emotions can be consciously and unconsciously evoked by specific events. Our experiences of these events send messages to our brains which in turn interpret the message and trigger basic human emotions like anger, fear, happiness, disgust, sadness, and more. is also one of those experiences that could evoke emotions and what’s a better way to use language than telling stories? Studies Language An engaging story won’t only grab the attention of the reader but it’ll also move them to . This is the kind of effect you want your stories to have on your customers. action "At its very core, marketing is storytelling. The best advertising campaigns take us on an emotional journey — appealing to our wants, needs, and desires — while at the same time telling us about a product or service." - Melinda Partin, Customer Experience Design and Marketing Consultant 3. Great Marketing Goes Beyond Selling The Product While it’s natural for marketing teams to want to talk about their new, amazing products to anyone who cares to listen, that’s not marketing that converts. It’s not the kind of marketing that makes your brand unforgettable or distinguishes you in a fiercely competitive environment. Great marketing seeks to build trust, a community, and credibility, all while remaining memorable. By telling beautifully crafted stories, you allow your customers to discover more than just what you sell. It’s just like dating — if all you do is talk about what you do, at what point does your date meet the real you? There’s no hope for an emotional connection in that case. When you communicate your brand’s values and mission through stories, your brand becomes more relatable and accessible. Members of your audience that resonate with those values and the inspiration behind your offerings will undoubtedly pitch a tent with your brand. This is one surefire way to build . brand loyalty You might worry that this would put off people who do not share the same values but a great marketing strategy is to build something 100 people will love and not something 1 million people may like. 4. People Want to Know How Your Brand is Impacting the World Little to no research will have you discovering that no matter how innovative or ‘ground-breaking’ your offering is, there are several others offering the same things in the global marketplace. Companies are spending a considerable percentage of their revenue just to get their brands in the faces of the right people and experience has proven that the best way to make this happen is to stand out. One way to stand out is to highlight how your product or service is impacting the world and making lives easier. This is a marketing strategy called social proof and according to , it remains a powerful tool for encouraging both online and offline sales. One way to communicate this social proof is through the art of storytelling — particularly through well-crafted success stories, testimonials, and even case studies. Gartner People will undoubtedly relate better with the experiences of others that are just like them. Final Thoughts If there’s one thing you must take away from this article, it’s that your audience needs to see a story about a relatable pain point and how your brand solves it. If widening your visibility, remaining unforgettable, increasing revenue and making impact are included in your brand objectives, then brand storytelling is the way to go. You absolutely cannot go wrong with it. This article was co-authored by Kolawole Samuel Adebayo

Why Tech Brands Should Worry About Storytelling

Indian Currency and Finance: Chapter IV

The gig economy continues to thrive post-pandemic. As we wave goodbye to the traditional nine to five, a flexible future seems to be on the cards for an evolving corporate sector. In fact, is now part of the gig economy in a post-covid working landscape. As experts predict that number will reach half by 2027, flexible working alternatives are quickly becoming the norm. 36% of the US workforce (Image Source: ) Mastercard Newsroom As you can see above, the gig economy is projected to grow to $455 billion by the end of 2023, especially on the back of corporate digitalisation trends that aim to improve remote working. The question is, just how effective could the gig economy be for start-up leaders looking to take off in a competitive corporate arena? We have collated our top tips on how to utilise the gig economy as a start-up and explored why it could be the key to flexible success. What Is Gig Economy? According to Investopedia, “in a gig economy, temporary, flexible jobs are commonplace and companies tend to hire independent contractors and freelancers instead of full-time employees.” A gig economy can be described as a free market system that aims to build flexible professional relationships on an Adhoc basis. While it tends to facilitate short term employment, start-up leaders are beginning to use the gig economy on a long term basis as they fight to stay afloat post-pandemic. There are a number of gig economy based platforms that facilitate the flexible working boom. From skill gap fillers such as Kolabtree to the freelance directory, Upwork, working and hiring within the gig economy has never been easier. (Image Source: ) Buffer After a recent Buffer study found that 32% of the post-pandemic workers surveyed valued flexibility the most within their role, there has never been a better time for entrepreneurs to jump onto the gig train and start offering flexible working schemes. Gig Economy’s Post-Pandemic Success In a post-pandemic corporate sector, it is no secret that remote working has prospered in response to Covid-19’s push for digitalisation. In fact, claim that remote working teams are the new norm post-2020. Not only have studies revealed that working from home has boosted corporate productivity, but experts suggest that a better work-life balance has rendered the trend all the more favourable for both the employer and the employee. 85% of corporate managers On the back of a flexible working boom, the gig economy is also thriving in a post-pandemic environment. After lost their jobs in 2020 alone, the gig economy quickly become a backup plan for a number of skilled workers seeking short term, flexible opportunities in an uncertain corporate landscape. 114 million Americans In 2020 alone, of the US workforce joined the gig economy. As gig platforms pooled with skilled specialists, it wasn't long before low budget start-ups started utilising its benefits. 12% Could Gig Economy Be The Key To Start-Up Success? From a global talent pool to the no-commitment policy, the gig economy has quickly become a fast-tracked hiring tool for looking to dip their tow into the corporate sector without getting stung. Read on as we delve into the benefits of utilising the gig economy as a start-up and how you can start tomorrow. new entrepreneurs A Global Skill Pool As a start-up manager, you’ll know just how hard it is to break into a competitive corporate sector. When battling against commerce giants and sizable workforces, it can be tough to stand out from the crowd. Luckily, the gig economy could be a ticket to triumph. If you want your business to get off of the ground in a short amount of time, hiring skilled experts within your field on an Adhoc basis provides your company with a value-producing workforce for only a fraction of the cost. Better still, post-Covid digitalisation has brought global hiring into the front and centre. Employers can now utilise the gig economy to hire specialists across the world, opening the talent pool up to a globally skilled workforce. Improving Fast-Track Hiring Unlike the standard hiring process, gig workers require little to no training as they tend to be experts within their field and are used to hopping from one project to another. Therefore, start-up employers are able to quickly hire and fire in a gig work partnership. Flexible hires are great for short term tasks and deadlines that need to be completed to precision in a quick turnover. They are here strictly for business and can aid start-ups to achieve their milestones faster. Grow Without Commitment With embarking on a start-up venture, comes significant risk. On the back of the pandemic, the corporate sector has seen a start-up boom, meaning more competition and a lower success rate. In fact, fail each year due to a lack of funding, competitive niches or a low skilled or lacking workforce. 20% of start-ups In such uncertain times for new entrepreneurs on the block, the gig economy provides business leaders with the opportunity to hire on an Adhoc basis in order to boost one aspect of the business, without dredging funding from another sector to pay a monthly wage. While gig work is flexible for the employee, it is also flexible for the employer. If times get hard and cash gets tight, start-up leaders can end partnerships quickly and efficiently with no strings attached. As we step into a flexible future, it’s clear that gig work is here to stay. With corporate competition at an all-time high, start-up leaders need to be prepared to take skilled work where they can get it if they are to keep up with the giants dominating the sector.

How To Utilise Gig Economy As A Start-up For Flexible Success

Multiple models trained on your data perform surprisingly poorly, despite having decent metrics on the validation set. The code seems fine, so you decide to take a closer look at your training data. You check a random sample - the label is wrong. So is the next. Your stomach sinks and you start looking through your data in batches*. Thirty minutes later, you realize that x% of your data is incorrect. Unfortunately this I've been in this situation a few too many times. Creating datasets is hard, even for relatively simple tasks like document classification/sentiment analysis etc. Not only do you have to worry about stuff like annotator bias, but label noise is insidious. You can measure label noise with annotator agreement metrics**, but even a relatively high agreement score can allow for ~10% of your data to be wrong. A good example of this is SST5, where classification performance is significantly worse than SST2 This problem can be even worse if you don't have very clearly defined orthogonal classes - It's relatively easy to come up with a labelling scheme that has a large amount of overlap between classes - this normally results in a lot of variance between annotators as each annotator will overrepresent a single class. For example, if you're building sentiment analysis models for survey results, how do you deal with the fact that 30% of your data might have customers complaining about your after-sales support but also complementing the fact that you're the most affordable option on the market? Do you switch to an aspect-based sentiment approach? If not, do you mark that sample as neutral? Irrespective of the judgement call that you take, how do you ensure that the annotators can be aligned to take similar judgement calls? A lot of companies I've done contract work for, default to Mturk for annotations. I think that this is a particularly bad idea - MTurk can be very unreliable and needs a lot of effort to ensure that you get high-quality annotations. With MTurk, you don't have a strong ability to train the annotators and align them with your requirements, and while you can restrict the regions where you get workers from - you can't be sure that they have the kinds of information that you need without directly testing it. Finally, if you do decide to test it, how do you ensure that the care/attention the annotators pay to the qualification tests will be maintained through every sample that they annotate? In my experience, the best thing to do is hire a set of annotators. That's hard too, but once you eventually figure out the hiring, here's some things that I've learned managing annotators. - In particular, task specific training is super useful. The best way I've found to do this, is to walk them through some sample annotations, give them a set to do independently and discuss what you think they could have done differently. I often need to do multiple iterations of this. Additionally, spending time communicating the overall project idea and helping them understand just how important the task is (despite the peanuts they're paid) leads to better results. Spend time training annotators . The easiest way to do this is to annotate a few hundred samples manually and document your thought process. I've found that drawing decision trees for a set of samples really helps communicate the thought process. Put a lot of effort into your annotation guidelines . Very often, getting a minimal set of data annotated, and trying to build models on it, will help target the specific kinds of annotated data that you need, or even bad classifiers can help filter through a lot of data and save you annotation time. Annotating a lot of data all at once limits the kinds of things you can do with the data. Prepare to do annotations in cycles . For example, used human annotators to rate how well an error correction system was working and they would present samples that they knew had errors in them at regular intervals to check if the annotators were paying enough attention. In cases where you can't directly calculate agreement, figure out ways to test annotators at irregular intervals Napoles et al - I used to like to expect a throughput of N samples/week. This led to significantly lower quality as they would rush to complete a week's worth of samples in a day or less and make a lot of mistakes. Frequent check-ins every two to three days helps. I've toyed with the idea of having the annotators use a web app and track database insertions to flag large spikes in activity - but for the moment it seems a little Orwellian. Frequent deadlines/followups . I've been a big fan of using just straight Google Docs/Excel etc because it seemed like the most straightforward solution, but when you have multiple annotators hopping on and off the project, a large pool of unlabelled data that needs to be stratified along multiple factors and also need to maintain a specific overlap between annotators handling all the different sheets is a nightmare. A lot of annotation tools exist - they all mostly do the same thing and they're all relatively inflexible. Roll your own if you have to, it's relatively easy with whatever web framework you're familiar with. Find the right tooling . Recommend having pairs of three annotators - where two annotators create the annotation, and a third annotator consolidates the samples to create the golden set. Unfortunately this didn't work for our lab in practice - we found that the individual that we had consolidate annotations was rather unreliable. Annotator overlap and evaluations Roit et al *This is a decent way to get an idea of your data, you essentially figure out the number of errors per batch and evaluate as many batches as you need to until you get a stable average value. You can then run a significance test to make sure that the average is representative if you want to be very thorough, but it usually is. **Agreement metrics essentially evaluate what proportion of your labels annotators agree about after adjusting for agreement based on pure chance. Photo by on Jan Antonin Kolar Unsplash

Stories, News & Mentions about KOLA

Kola’s Stories on HackerNoon