Hindustan Aeronautics Limited (HAL) has appointed Barenya Senapati as its new Director (Finance). Senapati has 29 years of experience and previously held the position of Executive Director (Finance).

HAL Appoints Barenya Senapati as New Director (Finance): Rediff Moneynews

HAL appoints Barenya Senapati as Finance Director, bringing extensive experience in accounting, financial planning, and treasury management.

Hindustan Aeronautics Ltd (HAL) has announced the appointment of Barenya Senapati as the Finance Director. - The Hindu BusinessLine

The Defence Ministry has approved a Rs 60,000 crore upgrade of India&#x27;s Su-30MKI fighter jet fleet, led by HAL and supported by DRDO. This project aims to enhance the aircraft&#x27;s capabilities with new radars, mission control systems, and weapon systems, reflecting India&#x27;s push for self-reliance ...

Sukhoi fighter jet: IAF's Sukhoi fighter jets to get a Rs 60,000 crore booster: Here are all the upgrades for the new Su-30MKI - The Economic Times

HAL Dividend 2024, Hindustan Aeronautics Dividend Record Date: The counter has a 52-week high of Rs 3,130 and a 52-week low of Rs 1,237.

Rs 22 Dividend: HAL shares fall over 1% as stock trades ex-date today | Zee Business

HAL dividend record date 2024: HAL had announced an interim dividend of 440 per cent, or Rs 22 per equity share earlier this month. ​Regarding the record date for HAL&#x27;s interim dividend, the corporation has said that, &quot;as informed earlier, record date for the payment of first interim dividend ...

HAL Shares Nearing Dividend Record Date; Know Last Date To Avail 440 pc Monetary Reward | Markets News, Times Now

HAL is willing to recruit qualified applicants for the position of GDMO for a period of 2 years. There are 02 vacant seats for the mentioned post.

HAL Recruitment 2024: Notification Out, Check Post, Qualification, Salary and Process to Apply

The Defence Acquisition Council (DAC) led by Defence Minister Rajnath Singh has given the green light to capital acquisition proposals worth Rs 84,560 crore to enhance the strength of the Armed Forces and Indian Coast Guard. The approval emphasizes the nations commitment to self-reliance by ...

HAL, BEL, BDL: Defence Stocks To Be In Focus Next Week; A Rs 80,000 Crore Order May Drive Bulls! - Goodreturns

At 1325 hours on Friday, HAL's scrip was trading 2% higher at Rs 3,086 while BEL's scrip on BSE was also trading 2% higher at Rs 189.85

HAL, BEL stocks rise 2% amid Defence Acquisition Council's likely nod for equipment worth Rs 80,000 cr

Since I started working for , I have tried to deepen my understanding of REST via various means. Did you read my review of ? Apache APISIX API Design Patterns book In the current literature, REST is generally promoted as the best thing since sliced bread. Yet, it comes with lots of challenges. In 2010(!), Martin Fowler wrote a post on the . He lists three steps for an API to become REST: glory of REST truly In each of these steps, issues lurk. This blog post focuses on listing some of them and providing hints at ways to solve them. Resources REST emerged from the cons of SOAP. SOAP provides a single endpoint and executes code depending on the payload. The idea of REST is to provide multiple endpoints, which each executes different code. I'll be honest; there are a few issues at this stage. The biggest one relates to guessing one identity from an existing one. If resource ids are sequential or even only numeric, it's easy to guess other resources' endpoints, , from to . e.g. /customers/1 /customers/2 The solution is to use non-sequential non-numeric ids, , . i.e. Universally unique identifiers Let's walk up the REST maturity model. HTTP Verbs HTTP verbs are the next step toward the glory of REST. They come from interactions with HTML "back in the day". Interactions came from Create Read Update Delete(CRUD) operations. It's pretty straightforward: Operation Verb Create POST Read GET Update PUT PATCH Delete DELETE The main problem with APIs is that you need to go beyond CRUD. Let's imagine a concrete example with a bank transfer: it takes money from one account and moves it to another one. How shall we model it? We could use the origin account as the resource, , . The target account, the amount, etc., can be passed as query parameters or in the body. But what HTTP verb shall we use? e.g. /accounts/a1b2c3d4e5f6 It changes the identified resource indeed, but it has "side-effects": it also changes another resource, the target account. Here are a couple of options on how to manage the HTTP verb: Use because it changes the source resource. It's misleading because it doesn't tell about side effects. POST Use a dedicated HTTP verb, , . It's not self-explanatory and is opposite to REST principles. e.g. TRANSFER Use with a so-called . Custom methods are a Google : POST custom method API Improvement Proposal Custom methods should only be used for functionality that can not be easily expressed via standard methods; prefer standard methods if possible, due to their consistent semantics. The HTTP URI use a character followed by the custom verb. must : Here's our bank account transfer URI: . /accounts/a1b2c3d4e5f6:transfer What's the best alternative? "It depends". Hypermedia Fowler describes Hypermedia Controls as the ultimate step to reaching the glory of REST. It's nowadays known as Hypermedia As The Engine of Application State(HATEOAS): With HATEOAS, a client interacts with a network application whose application servers provide information dynamically through hypermedia. A REST client needs little to no prior knowledge about how to interact with an application or server beyond a generic understanding of hypermedia. -- HATEOAS on Wikipedia HATEOAS is a concept; here's a possible implementation taken from Wikipedia. When one requests a bank account, say , the response contains links to actions possible with this specific bank account: /accounts/a1b2c3d4e5f6 {
 "account": {
 "account_number": "a1b2c3d4e5f6",
 "balance": {
 "currency": "USD",
 "value": 100.00
 },
 "links": {
 "_self": "/accounts/a1b2c3d4e5f6",
 "deposit": "/accounts/a1b2c3d4e5f6:deposit",
 "withdrawal": "/accounts/a1b2c3d4e5f6:withdrawal",
 "transfer": "/accounts/a1b2c3d4e5f6:transfer",
 "close-request": "/accounts/a1b2c3d4e5f6:close-request"
 }
 }
} If the balance is negative, only the deposit link will be available: {
 "account": {
 "account_number": "a1b2c3d4e5f6",
 "balance": {
 "currency": "USD",
 "value": 100.00
 },
 "links": {
 "_self": "/accounts/a1b2c3d4e5f6",
 "deposit": "/accounts/a1b2c3d4e5f6:deposit",
 }
 }
} A common issue with REST is the lack of standards; HATEOAS is no different. The first attempt to bring some degree of standardization was the , HAL. Note that it was incepted in 2012; the latest version dates from 2016, and it's still in draft. JSON Hypertext Application Language aka Here's a quick diagram that summarizes the proposal: We can rework the above with HAL as the following: GET /accounts/a1b2c3d4e5f6 HTTP/1.1
Accept: application/hal+json

HTTP/1.1 200 OK
Content-Type: application/hal+json

{
 "account": {
 "account_number": "a1b2c3d4e5f6",
 "balance": {
 "currency": "USD",
 "value": 100.00
 },
 "_links": { <1>
 "self": { <2>
 "href" : "/accounts/a1b2c3d4e5f6",
 "methods": ["GET"] <3>
 },
 "deposit": {
 "href" : "/accounts/a1b2c3d4e5f6:deposit", <4>
 "methods": ["POST"] <3>
 }
 }
 }
} Available links Link to self Tell which HTTP verb can be used Link to deposit Another attempt at standardization is , Web Linking. It describes the format and contains a , , and . The most significant difference with HAL is that RFC 8288 communicates links via HTTP response headers. RFC 8288 aka link relationship registry e.g. alternate copyright HTTP/2 200 OK

Link: </accounts/a1b2c3d4e5f6> rel="self";
 method="GET", <1>
 </accounts/a1b2c3d4e5f6:deposit> rel="https://my.bank/deposit";
 title="Deposit";
 method="POST" <2>
{
 "account": {
 "account_number": "a1b2c3d4e5f6",
 "balance": {
 "currency": "USD",
 "value": 100.00
 }
 }
} Link to the current resource with the non-standard relation type self Link to deposit with the extension relation type and an arbitrary target attribute https://my.bank/deposit title Other alternative media types specifications are available. Name Description Provided by Uniform Basis for Exchanging Representations The UBER document format is a minimal read/write hypermedia type designed to support simple state transfers and ad-hoc hypermedia-based transitions. This specification describes both the XML and JSON variants of the format and provides guidelines for supporting UBER-encoded messages over the HTTP protocol. Individuals Collection+JSON Collection+JSON is a JSON-based read/write hypermedia-type designed to support the management and querying of simple collections Individual JSON: API JSON: API is a specification for how a client should request that resources be fetched or modified, and how a server should respond to those requests. JSON: API can be easily extended with extensions and profiles. Individuals Siren Siren is a hypermedia specification for representing entities. As HTML is used for visually representing documents on a Web site, Siren is a specification for presenting entities via a Web API. Siren offers structures to communicate information about entities, actions for executing state transitions, and links for client navigation. Individual Application-Level Profile Semantics An ALPS document can be used as a profile to explain the application semantics of a document with an application-agnostic media type (such as HTML, HAL, Collection+JSON, Siren, etc.). This increases the reusability of profile documents across media types. IETF Bonus: HTTP Response Status What Fowler's post doesn't mention is the HTTP response status. Most readers are familiar with the status ranges: Informational responses: 100 – 199 Successful responses: 200 – 299 Redirection messages: 300 – 399 Client error responses: 400 – 499 Server error responses: 500 – 599 Likewise, most are also with regularly-found HTTP status: , 200 OK , 301 Moved Permanently , 302 Found , 401 Unauthorized , 403 Forbidden and 404 Not Found . 500 Internal Server Error The problem is that beyond these simple cases, it's a mess. For example, look at this : "Which HTTP status code means Not Ready Yet, Try Again Later?" Here is a summary of the proposed answers, from the most upvoted to the lowest: StackOverflow question 503 Service Unavailable 202 Accepted (accepted answer) 423 Locked 404 Not Found 302 Found 409 Conflict 501 Not Implemented (downvoted) It's not a straightforward answer; there was a lot of debate around the alternatives. For the record, I think the accepted answer is the right one. That's already a lot on the designer side, but the client side contains a lot of uncertainty, too, as some big APIs providers use their . own HTTP status codes Conclusion The "glory of REST" doesn't mean much. There's no univocal semantics to rely on, despite any opposite claim. As it is, it depends mainly on the implementation and interpretation: both require documenting the custom behavior instead of relying on a shared specification. SOAP's biggest flaw was its complexity and its focus on big companies, but it at least provided a shared set of standard specifications. The industry replaced it with REST, not a specification but an architectural site. REST is simpler and, thus, more approachable, but it requires a lot of custom effort, which changes from project to project. There are initiatives to provide some standardization, but they are few, and some are at odds with others. Moreover, they have low traction, so people don't know them, which creates a vicious circle. I hardly advocate getting back to SOAP, though I sure miss it sometimes. Originally published at on January 22nd, 2023 A Java Geek

The Glory of REST: Is It Really That Glorious? 

The story goes that Caesar, to exchange secret messages with his generals in the field, used to shave his messengers bald and write the message on their scalps. He would then wait a few months for their hair to grow back and send them off to their destinations. Only his trusted generals would know of this method to exchange messages, thus delivering his orders securely (albeit a few months late). This impractical, and rather silly, example describes what cryptology is all about. Cryptology is the science of securing communication. The term is taken from the Greek ("hidden, secret") and ("word"). In essence, it is about "hiding words". It is only one pillar in the science of Cybersecurity, but it is a significant one. At the base of this pillar are the subdivisions of cryptology: Cryptography and Cryptanalysis. The two can almost be seen as complementary. Where cryptography is the practice of transforming communications into a form that is unreadable to eavesdroppers, cryptanalysis is the practice of trying to unravel those transformed messages by an unintended recipient. kryptós lógos And it is here, at the base of this pillar, where one proof of a problem could cause the collapse of Cybersecurity. So, enter the Pantheon, this temple of Cybersecurity if you will, and let me guide you to where the cracks in the Corinthian columns begin to show. There are many different algorithms designed to keep messages secure. I'm going to tell you a bit about some of those systems so that the foundation of these algorithms becomes clear. If you've read anything about cryptography, chances are you've come across a concept called the "Caesar cipher". This is another example of a method used to secure messages. It is also attributed to Caesar, although this one doesn't involve a messenger's locks (pun intended) to keep the message safe. Instead, this cipher introduces an important concept that a significant portion of cryptographic algorithms are based on: Modular Arithmetic. I know, I know. It sounds scary, right? What if I told you, it's so simple that you use it every day? See, your clock is based on modular arithmetic as well. When you're trying to figure out how much sleep you're going to get if you have to wake up at 06:00, as you're finishing up that deadline at 23:00, you know not to count past 24:00. The result is always going to be less than 24:00. You're essentially calculating modulo 24. This is modular arithmetic, and it is used extensively in cryptography. Even in its simplicity, though, modular arithmetic holds many secrets that aren't immediately evident. Many cryptographic algorithms rely on these secrets. Caesar's cipher is a symmetric cipher. This means that both parties use the same key. Let's say the key is 3. The sender would shift every letter of his message by 3. This is called encryption. The receiver needs to know the key, and would then shift back every letter by 3, obtaining the original message. This is called decryption. Compare this to the bald messenger method. Encryption is letting the messenger's hair grow over the message, decryption is shaving the messenger bald. Now, is the Caesar cipher very secure? Well, not really. Anyone can easily try all the different keys, of which there are 26 in total, and find the correct one to unravel the message. This is called a Brute Force Attack. While the cipher is not very secure, it does adhere to an important principle that Caesar's bald messengers do not adhere to. Kerckhoffs principle states: "A cipher should not require secrecy, and it should not be a problem if it falls into enemy hands." In other words, the principle states that only the key should remain secret. The method may be made public, but without the key, the message should remain secure. If Caesar's formerly bald messenger gets intercepted by the enemy and the interceptor is aware of the method used by Caesar, the poor messenger will be shaved bald again in no time, revealing the message on his scalp. With Caesar's cipher, however, even if the interceptor knows the method of encryption, he would still have to try 26 different keys to uncover the message. Caesar's cipher is one of the simplest ciphers in existence, but its simplicity nicely demonstrates aspects of modular arithmetic. Other common symmetric cryptosystems are DES, 3DES, and AES. They essentially do the same thing as Caesar's cipher, albeit way more complex and harder to brute force. If you want to read more about these systems, I highly recommend reading the . AES Comic Let's introduce another important concept. Asymmetric cryptography (or public-key cryptography). The difference is that instead of the two parties having the same key, they have their own public and secret keys. Before we dive into RSA, here's a cool tidbit about it for you. When RSA was invented by Ron Rivest, Adi Shamir, and Leonard Adleman, it was illegal for them to export the algorithm or even its description, as part of munitions control in the US. RSA was considered so powerful that it was to be kept a military secret. As a freedom of speech protest, they wore T-shirts with the algorithm printed on them to conventions and talks. RSA is the most popular public-key cryptosystem. It's a super cool system that perfectly illustrates what a lot of modern cryptography is based on. We're going to get a bit technical here but bear with me. The fundamental theorem of arithmetic states that any positive number can be represented in exactly one way as a product of one or more primes. For example, the number 77 can be represented by multiplication of 7 (a prime) and 11 (a prime). There is no other way to represent 77 in primes apart from changing the order of the primes. Keep this in mind while I explain RSA. Before a message can be sent, we need to do some setup. Say, Bob wants to send a message to Alice and there is some eavesdropper called Eve. Alice, as the receiver, chooses two large prime numbers. She multiplies these two numbers to get the result m, the modulus. We're going to keep it simple and small in our example. Alice chooses 7 and 11 as prime numbers, resulting in the modulus 77. She publishes the modulus 77 and some chosen encryption exponent e. The combination of the modulus 77 and the encryption exponent e is called her public key. With Alice's public key Bob can encrypt the message he wants to send. In this case, the message is a number x. Encryption in RSA is done by taking x^e mod m. This results in ciphertext y and sends this to Alice. Now, Alice can do some magic with the prime factors 7 and 11, which results in a piece of information called d (for decryption). This is Alice's secret key. All Alice has to do now is take y^d, which will result in Bob's original message x. Phew, that was a lot, but the hard part is over! Now, notice that only Alice knows prime factors 7 and 11. This means that only Alice can do that magic trick to get information d.  But if you're sharp you would disagree with me here. You'd say: "Since 77 is published and everyone has access to it, Eve can easily figure out that 77 = 7*11 and do the magic trick as well to obtain d, with which she can get the original message x". I would agree with you here. Then I would tell you: "What are the primes of the number 30142741". Chances are you won't be able to tell me the answer. I can very easily tell you the answer though since all I did was take two prime numbers and multiply them to get 30142741.  And if I told you those two numbers, you could just as easily verify that the product is 30142741. So indeed, RSA relies on Eve (or you) not being able to find those two primes. In this case, the primes are 6037 and 4993. See how difficult prime factorization is, but how easy it is to verify the correct primes? That's it!  We are finally at the base of the pillar. Do you see the cracks? Probably not. Let me clarify. So, the transformations we apply to the message (encryption) need to be invertible for the receiver to be able to decrypt it. The receiver can invert the message because she is in possession of some extra information. Meanwhile, any interceptor, not in possession of that information, will not be able to decrypt the message. In RSA, for example, the interceptor would need to find the two prime factors of the modulus. Finding the two prime factors of a small number like 77 is, of course, easy, but prime factorization becomes much harder when a large number is chosen. Verifying that the two primes are factors of the modulus is always relatively easy since you just do multiplications. If prime factorization was easy or if there was an algorithm that can solve the problem relatively fast, then RSA would become obsolete. It relies on prime factorization being hard to solve, but easy to verify. We can make a distinction between two sets of problems. There are problems for which we know a way to find the answer quickly, for example, multiplication or squaring. This set is called "class P". The other class, "NP" is a set of problems for which there are no known ways to find an answer quickly, but when you have some information, the answer is easily verifiable. Prime factorization belongs to this class. But what if there is a way to solve a prime factorization problem easily? This would imply that prime factorization belongs to the P class. In fact, maybe we could prove that all NP problems are actually P problems. The conclusion would be that P = NP. This conclusion would have disastrous consequences for cryptography. As we've seen, RSA relies on prime factorization being difficult to solve. But RSA is only one of many algorithms that rely on NP problems and prime factorization is only one example of an NP problem. Other symmetric and asymmetric ciphers used for your financial transactions, your e-mail communication, etc. would be rendered obsolete. Bitcoin and other cryptocurrencies would suffer severe consequences as well since Bitcoin relies on cryptographic hashing, specifically, the SHA-256 hashing algorithm. For a new block to be accepted in the blockchain, this new block needs to contain a proof-of-work. In short, the proof is easy for any node in the network to verify, but generating the correct number is extremely hard. Proof of P = NP could on the other hand have positive consequences for other fields. Many mathematical problems remain hard to solve. Just imagine the effects it could have on mathematics! Proof of P ≠ NP would mean that our cryptographic algorithms are secure and that the title of this article is just clickbait. But at least I offered you the chance to win a million dollars! That's the reward the Clay Mathematics Institute will award to the first person to solve the "P vs NP" problem. So, give it a shot! Maybe you could be the one to break modern cryptography and send us back to using bald messengers for our daily communication. Also Published Here

An Insecure Pillar in Cybersecurity

Un pilar resquebrajado en ciberseguridad

Un pilier non sécurisé de la cybersécurité

साइबर सुरक्षा में एक असुरक्षित स्तंभ

サイバーセキュリティにおける安全性の低い柱

Um Pilar Inseguro na Segurança Cibernética

Một trụ cột không an toàn trong an ninh mạng

网络安全中的不安全支柱

Halloween is the perfect time to add a touch of spooky fun to your website. You don’t need to go overboard with decorations, something as simple as changing your fonts can make a big impact. Most of the fonts shown are free to download, and to add them to your CSS, use the following code. @font-face {
    font-family: "font name",
    src: url("Extra Days.otf");
}

.font-family {
    font-family: "font name";       
} Font Tester Before you start, if you want to easily test out different local fonts you can use the font tester chrome extension. Not only does it become easier for you to choose a perfect font for Halloween, but provides you with a better understanding of typography. Download Font tester Bloody Hell Download Bloody hell Melted Monster Download Melted Monster Heartless Download Heartless Night core Download Night core Help Me Download Help me Frank knows Frank knows Exquisite corpse Download Exquisite corpse Monster Pumpkin Download Monster pumpkin Zombie Holocaust Zombie holocaust That’s it for now. If you have any more spooky fonts feel free to comment :) Halloween is the perfect time to add a touch of spooky fun to your website. You don’t need to go overboard with decorations, something as simple as changing your fonts can make a big impact. Most of the fonts shown are free to download, and to add them to your CSS, use the following code. @font-face {
    font-family: "font name",
    src: url("Extra Days.otf");
}

.font-family {
    font-family: "font name";       
} @font-face {
    font-family: "font name",
    src: url("Extra Days.otf");
}

.font-family {
    font-family: "font name";       
} Font Tester Before you start, if you want to easily test out different local fonts you can use the font tester chrome extension. Not only does it become easier for you to choose a perfect font for Halloween, but provides you with a better understanding of typography. Download Font tester Download Font tester Download Font tester Bloody Hell Download Bloody hell Download Bloody hell Download Bloody hell Melted Monster Download Melted Monster Download Melted Monster Download Melted Monster Heartless Download Heartless Download Heartless Download Heartless Night core Download Night core Download Night core Download Night core Help Me Download Help me Download Help me Download Help me Frank knows Frank knows Frank knows Frank knows Exquisite corpse Download Exquisite corpse Download Exquisite corpse Download Exquisite corpse Monster Pumpkin Download Monster pumpkin Download Monster pumpkin Download Monster pumpkin Zombie Holocaust Zombie holocaust Zombie holocaust Zombie holocaust That’s it for now. If you have any more spooky fonts feel free to comment :)

Top Spooky Fonts to Use for Your Website on Halloween 🎃

Overcome LLM Hallucinations Using Knowledge Bases

التغلب على الهلوسة باستخدام قواعد المعرفة

Überwinden Sie LLM-Halluzinationen mithilfe von Wissensdatenbanken

Supere las alucinaciones de LLM utilizando bases de conocimiento

Surmontez les hallucinations du LLM grâce aux bases de connaissances

Հաղթահարեք LLM հալյուցինացիաները՝ օգտագործելով գիտելիքների հիմքերը

知識ベースを使用して LLM 幻覚を克服する

Reseo ny Hallucinations LLM amin'ny fampiasana toby fahalalana

LLM Alucinaciones nisqakunata atipay Yachaypa Bases nisqawan

Depășiți halucinațiile LLM folosind baze de cunoștințe

දැනුම පදනම් භාවිතා කරමින් LLM මායාවන් ජය ගන්න

Övervinna LLM-hallucinationer med hjälp av kunskapsbaser

Shinda Ukumbi wa LLM Kwa Kutumia Misingi ya Maarifa

When I first set out on the entrepreneurial path, I had one goal: success. But after diving headfirst into the world of search funds and high-stakes startups, I found myself frustrated, drained, and questioning everything I’d come to believe about entrepreneurship. It wasn’t just that I wasn’t seeing the progress I’d envisioned—it was more personal. I felt like I was participating in a script that wasn’t written for me. My journey to create HalalFinanx wasn’t just about building a website; it was about reclaiming control, redefining success, and connecting to something meaningful. The Glamorous Illusion of Entrepreneurship Like many people, I was lured into entrepreneurship by the shiny allure of success stories and the promises of independence and financial freedom. Owning something, leading a team, and creating value sounded perfect. The search fund model was especially appealing, offering a structured path to find, acquire, and grow an existing business. It seemed like a straightforward formula with a lot of support. But as I dove deeper, the reality didn’t line up with the narrative. It felt like the supposed “freedom” of entrepreneurship was simply a myth, shackled by complex financial structures, endless pitching cycles, and a business environment that seemed more concerned with pleasing investors than creating something meaningful. I was constantly running from one “critical task” to another, but with no tangible progress. The whole structure of the search fund, built on layers of assumptions, started to feel like a game—and not the kind I wanted to play. The more I went, the more I felt like I was living someone else’s dream. I was chasing metrics that weren’t meaningful to me, jumping through hoops for outcomes that felt hollow. I started asking myself, “Is this what entrepreneurship is supposed to feel like?” I wanted out, but I didn’t know where to turn. Finding a New Path – The Birth of HalalFinanx The turning point came when I realized that if I wanted real change, I had to start creating things that resonated with me, not just my bank account or a pitch deck. As a Muslim, I’ve always been interested in Islamic finance, especially the ethical approach it brings to wealth. However understanding the field and accessing resources can be a challenge. I thought, why not create something to make Islamic finance easier to understand? I’ll be honest—this wasn’t the kind of idea that was going to impress traditional investors or fit into the typical startup. But for the first time, I was excited about what I was working on. I saw a real gap, not in a theoretical market sense, but a gap in what people genuinely needed. HalalFinanx was my way of bringing Islamic finance to the digital age in a way that’s accessible, understandable, and useful. There was one small issue: my skills lie in the backend and data. I’ve built and structured plenty of systems, but front-end work? Design? User experience? That was all new territory. Still, I knew that if I didn’t push myself here, I’d be back where I started—stuck in a rut, relying on others to bring my vision to life. This time, I was going to be in control. Learning by Doing – Building HalalFinanx with Bolt.new To get HalalFinanx off the ground, I turned to Bolt.new, a product that allowed me to work in a framework even with my limited front-end knowledge. Building this project was intense. I’d spend late nights combing through design guides, trying to make sure the site looked decent and functioned smoothly. It was exhausting, but the work felt real. This wasn’t just a project to show a board or potential investors—it was something I cared about personally, and every element I worked on felt like it added to that sense of fulfilment. Sure, there were plenty of challenges. Frontend work, it turns out, isn’t just about knowing which elements go where—it’s an art form. I struggled with layout, design principles, and even simple user flows. There were days when I’d look at the site and think, “This isn’t working.” But rather than giving up or passing the task to someone else, I forced myself to learn. It was a series of trial and error of building, testing, and iterating. What kept me going was the vision of what HalalFinanx could become, and each small win felt monumental. Making a button work, fixing a colour scheme, aligning content so it made sense—all of these were tiny victories in a larger war. The backend developer in me was learning to appreciate the nuances of frontend work, and it was humbling. The Personal Impact of Creating HalalFinanx This journey with HalalFinanx wasn’t just about building a site it was about redefining what success and fulfilment meant to me. In the search fund and traditional startup world, everything had been about numbers, KPIs, and keeping the right people happy. Here, with HalalFinanx, I was finally creating something with a purpose that resonated with me on a personal level. Building a site to provide accessible Islamic finance information was meaningful, not because of the potential returns or scalability, but because it filled a need I felt deeply. Each piece of content, each design tweak, and each function was geared towards making something simple, clear, and beneficial to anyone seeking this kind of financial guidance. I wasn’t answering to anyone but myself and my users, and that was liberating in a way I hadn’t expected. On a personal level, I found myself rediscovering why I wanted to create in the first place. I wanted to build something that mattered, and HalalFinanx became that for me. Instead of chasing empty metrics, I was now chasing real feedback from real users. Each suggestion and piece of feedback helped me refine the site, making it not just a project, but an evolving resource. For the first time, I was thinking long-term, not about exits or acquisition targets, but about sustainability and relevance. Looking Forward – The Ongoing Journey of HalalFinanx I don’t know where HalalFinanx will be in five years, but I know I’m in it for the long run. This isn’t a project that I’ll drop at the first sign of difficulty or when the next big thing comes along. It’s a genuine part of me now, a blend of my skills, my values, and my aspirations. I’m constantly looking for ways to improve it, from gathering user feedback to exploring new resources and insights to share. This journey taught me that real entrepreneurship isn’t about the numbers on a spreadsheet or the approval of others. It’s about finding something that matters to you, something you’re willing to build from scratch, without shortcuts or compromises. HalalFinanx is still a work in progress, but it’s my work, and that’s what makes it worth every bit of effort. When I first set out on the entrepreneurial path, I had one goal: success. But after diving headfirst into the world of search funds and high-stakes startups, I found myself frustrated, drained, and questioning everything I’d come to believe about entrepreneurship. It wasn’t just that I wasn’t seeing the progress I’d envisioned—it was more personal. I felt like I was participating in a script that wasn’t written for me. My journey to create HalalFinanx wasn’t just about building a website; it was about reclaiming control, redefining success, and connecting to something meaningful. The Glamorous Illusion of Entrepreneurship Like many people, I was lured into entrepreneurship by the shiny allure of success stories and the promises of independence and financial freedom. Owning something, leading a team, and creating value sounded perfect. The search fund model was especially appealing, offering a structured path to find, acquire, and grow an existing business. It seemed like a straightforward formula with a lot of support. But as I dove deeper, the reality didn’t line up with the narrative. It felt like the supposed “freedom” of entrepreneurship was simply a myth, shackled by complex financial structures, endless pitching cycles, and a business environment that seemed more concerned with pleasing investors than creating something meaningful. I was constantly running from one “critical task” to another, but with no tangible progress. The whole structure of the search fund, built on layers of assumptions, started to feel like a game—and not the kind I wanted to play. The more I went, the more I felt like I was living someone else’s dream. I was chasing metrics that weren’t meaningful to me, jumping through hoops for outcomes that felt hollow. I started asking myself, “Is this what entrepreneurship is supposed to feel like?” I wanted out, but I didn’t know where to turn. Finding a New Path – The Birth of HalalFinanx The turning point came when I realized that if I wanted real change, I had to start creating things that resonated with me, not just my bank account or a pitch deck. As a Muslim, I’ve always been interested in Islamic finance, especially the ethical approach it brings to wealth. However understanding the field and accessing resources can be a challenge. I thought, why not create something to make Islamic finance easier to understand? I’ll be honest—this wasn’t the kind of idea that was going to impress traditional investors or fit into the typical startup. But for the first time, I was excited about what I was working on. I saw a real gap, not in a theoretical market sense, but a gap in what people genuinely needed. HalalFinanx was my way of bringing Islamic finance to the digital age in a way that’s accessible, understandable, and useful. There was one small issue: my skills lie in the backend and data. I’ve built and structured plenty of systems, but front-end work? Design? User experience? That was all new territory. Still, I knew that if I didn’t push myself here, I’d be back where I started—stuck in a rut, relying on others to bring my vision to life. This time, I was going to be in control. Learning by Doing – Building HalalFinanx with Bolt.new To get HalalFinanx off the ground, I turned to Bolt.new, a product that allowed me to work in a framework even with my limited front-end knowledge. Building this project was intense. I’d spend late nights combing through design guides, trying to make sure the site looked decent and functioned smoothly. It was exhausting, but the work felt real. This wasn’t just a project to show a board or potential investors—it was something I cared about personally, and every element I worked on felt like it added to that sense of fulfilment. Sure, there were plenty of challenges. Frontend work, it turns out, isn’t just about knowing which elements go where—it’s an art form. I struggled with layout, design principles, and even simple user flows. There were days when I’d look at the site and think, “This isn’t working.” But rather than giving up or passing the task to someone else, I forced myself to learn. It was a series of trial and error of building, testing, and iterating. What kept me going was the vision of what HalalFinanx could become, and each small win felt monumental. Making a button work, fixing a colour scheme, aligning content so it made sense—all of these were tiny victories in a larger war. The backend developer in me was learning to appreciate the nuances of frontend work, and it was humbling. The Personal Impact of Creating HalalFinanx This journey with HalalFinanx wasn’t just about building a site it was about redefining what success and fulfilment meant to me. In the search fund and traditional startup world, everything had been about numbers, KPIs, and keeping the right people happy. Here, with HalalFinanx, I was finally creating something with a purpose that resonated with me on a personal level. Building a site to provide accessible Islamic finance information was meaningful, not because of the potential returns or scalability, but because it filled a need I felt deeply. Each piece of content, each design tweak, and each function was geared towards making something simple, clear, and beneficial to anyone seeking this kind of financial guidance. I wasn’t answering to anyone but myself and my users, and that was liberating in a way I hadn’t expected. On a personal level, I found myself rediscovering why I wanted to create in the first place. I wanted to build something that mattered, and HalalFinanx became that for me. Instead of chasing empty metrics, I was now chasing real feedback from real users. Each suggestion and piece of feedback helped me refine the site, making it not just a project, but an evolving resource. For the first time, I was thinking long-term, not about exits or acquisition targets, but about sustainability and relevance. Looking Forward – The Ongoing Journey of HalalFinanx I don’t know where HalalFinanx will be in five years, but I know I’m in it for the long run. This isn’t a project that I’ll drop at the first sign of difficulty or when the next big thing comes along. It’s a genuine part of me now, a blend of my skills, my values, and my aspirations. I’m constantly looking for ways to improve it, from gathering user feedback to exploring new resources and insights to share. This journey taught me that real entrepreneurship isn’t about the numbers on a spreadsheet or the approval of others. It’s about finding something that matters to you, something you’re willing to build from scratch, without shortcuts or compromises. HalalFinanx is still a work in progress, but it’s my work, and that’s what makes it worth every bit of effort.

Building HalalFinanx: A Journey from Disillusionment to Personal Fulfillment

One data scientist recently argued with me that we should stop using the term “hallucination” and just call these outputs what they really are: errors. The premise is simple—calling them errors would set more reasonable expectations for AI’s behavior. While this argument might make sense for someone coming from a statistics or programming background, it fundamentally misunderstands how AI works and why the term “hallucination” is actually more appropriate, albeit imperfect. The Misunderstanding of AI’s Nature From a statistical perspective, an error is a deviation from a known value or standard. It’s easy to quantify, easy to detect, and there’s a clear sense of right and wrong. If a model predicts a 20% probability when the true probability is 30%, we call it an error. We can measure this deviation, adjust the model, and move forward. For a data scientist accustomed to working within this framework, it’s natural to see LLM outputs that are factually incorrect as just another type of error. If an AI model says, “A circle has three sides,” then it’s clearly made a mistake—like a regression model producing a bizarre outlier. The problem with this comparison is that it applies a narrow definition of error to a system that generates language, not discrete values. AI models like GPT-4 do not “make errors” in the traditional sense because they lack a clear objective standard like those found in statistics. Why We Call It “Hallucination” AI language models generate sequences of tokens—words and phrases—based on probabilistic patterns. These patterns are learned from vast amounts of text data, and the models produce the most probable sequence of words given the context. Because of this structure, a language model might generate a phrase that is syntactically correct but semantically flawed. Imagine these two statements: “A circle has three sides.” “The professor said a circle has three sides.” If you evaluate these on a token-by-token basis, both might be highly probable outputs based on their preceding context. The first statement is objectively false, while the second statement could be contextually true if a professor actually made that erroneous claim. The model doesn’t have an internal understanding of geometry or truth—it’s simply generating words that fit together well. That’s why when the output is nonsense, we call it a “hallucination” instead of an error. The model didn’t make a mistake according to its own mechanics; it just produced an improbable yet plausible-sounding string of text. The Inadequacy of Calling It “Error” Labeling such outputs as errors creates the false impression that these models should know better. But knowing requires understanding, and that’s not how AI models are built. They don’t “know” in the way humans do, nor do they validate statements against a factual baseline. There is no inherent “truth” within the architecture of an LLM. The model operates based on patterns and associations, not logical consistency or factual accuracy. When I hear the argument that AI hallucinations are “logical errors” or “input errors,” it reminds me of the Garbage In, Garbage Out (GIGO) adage in traditional programming. If your inputs are flawed or your logical framework is off, the system produces wrong outputs. But that analogy only goes so far with AI because language and context are far more nuanced than a spreadsheet of values or a database query. An LLM doesn’t make logical errors in the programming sense. Instead, it lacks an internal verification process to ensure that what it’s saying is true. Imagine trying to apply the same logic to artistic styles or creativity. If an AI-generated image combines elements of a cat and a cloud, calling it an “error” is inappropriate. The model didn’t err—it produced a plausible but nonsensical creation based on its input data and generative process. Hallucinations and Human Perception This distinction is crucial because calling these outputs “errors” could mislead people into thinking that LLMs are making simple mistakes that can be fixed with better logic or more data. But hallucinations in LLMs are not bugs that can be patched. They are a byproduct of how these models work—of generating text without a built-in sense of truth. The onus is still on the human user to guide the AI’s output by crafting better prompts, setting clearer parameters, and using post-processing tools to verify facts. This is why the term “hallucination,” while imperfect, is closer to the mark. It conveys that the model is not just producing an error but fabricating new content—fabrications that are a natural consequence of its design, not the result of poor logic or faulty inputs. It serves as a reminder that these models are generative, not analytical. They don’t have a grasp of reality and can produce completely fabricated content even when all the inputs seem perfect. Setting Expectations for AI’s Outputs Ultimately, the data scientist’s argument comes from a place of wanting to simplify AI’s behaviors for the end-user. If we call these outputs “errors,” maybe people will understand AI’s limitations better. But in reality, this simplification does a disservice to the complexity of these models. We need to help people understand that AI models do not think, reason, or understand—they predict and generate. Their hallucinations are not “errors” in a mechanical or statistical sense but are intrinsic artifacts of how they operate. Until we develop AI models with built-in mechanisms for validating truth, we will continue to see outputs that are not just factually wrong but sometimes fantastical. And as we refine our language and expectations around AI, we need to keep terms like “hallucination” in place—if only to remind ourselves that these models are not yet capable of true understanding. So, while I appreciate the sentiment behind labeling these outputs as errors, it inadvertently strips away the nuances that make AI hallucinations fundamentally different from the statistical errors many data scientists are familiar with. As we continue to refine our models and our language, it’s worth keeping these distinctions in mind to set clearer expectations for what AI can and cannot do. About Me: 25+ year IT veteran combining data, AI, risk management, strategy, and education. 4x hackathon winner and social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com One data scientist recently argued with me that we should stop using the term “hallucination” and just call these outputs what they really are: errors. The premise is simple—calling them errors would set more reasonable expectations for AI’s behavior. While this argument might make sense for someone coming from a statistics or programming background, it fundamentally misunderstands how AI works and why the term “hallucination” is actually more appropriate, albeit imperfect. The Misunderstanding of AI’s Nature From a statistical perspective, an error is a deviation from a known value or standard. It’s easy to quantify, easy to detect, and there’s a clear sense of right and wrong. If a model predicts a 20% probability when the true probability is 30%, we call it an error. We can measure this deviation, adjust the model, and move forward. For a data scientist accustomed to working within this framework, it’s natural to see LLM outputs that are factually incorrect as just another type of error. If an AI model says, “A circle has three sides,” then it’s clearly made a mistake—like a regression model producing a bizarre outlier. The problem with this comparison is that it applies a narrow definition of error to a system that generates language, not discrete values. AI models like GPT-4 do not “make errors” in the traditional sense because they lack a clear objective standard like those found in statistics. Why We Call It “Hallucination” AI language models generate sequences of tokens—words and phrases—based on probabilistic patterns. These patterns are learned from vast amounts of text data, and the models produce the most probable sequence of words given the context. Because of this structure, a language model might generate a phrase that is syntactically correct but semantically flawed. Imagine these two statements: “A circle has three sides.” “The professor said a circle has three sides.” If you evaluate these on a token-by-token basis, both might be highly probable outputs based on their preceding context. The first statement is objectively false, while the second statement could be contextually true if a professor actually made that erroneous claim. The model doesn’t have an internal understanding of geometry or truth—it’s simply generating words that fit together well. That’s why when the output is nonsense, we call it a “hallucination” instead of an error. The model didn’t make a mistake according to its own mechanics; it just produced an improbable yet plausible-sounding string of text. The Inadequacy of Calling It “Error” Labeling such outputs as errors creates the false impression that these models should know better. But knowing requires understanding, and that’s not how AI models are built. They don’t “know” in the way humans do, nor do they validate statements against a factual baseline. There is no inherent “truth” within the architecture of an LLM. The model operates based on patterns and associations, not logical consistency or factual accuracy. When I hear the argument that AI hallucinations are “logical errors” or “input errors,” it reminds me of the Garbage In, Garbage Out (GIGO) adage in traditional programming. If your inputs are flawed or your logical framework is off, the system produces wrong outputs. But that analogy only goes so far with AI because language and context are far more nuanced than a spreadsheet of values or a database query. An LLM doesn’t make logical errors in the programming sense. Instead, it lacks an internal verification process to ensure that what it’s saying is true. Imagine trying to apply the same logic to artistic styles or creativity. If an AI-generated image combines elements of a cat and a cloud, calling it an “error” is inappropriate. The model didn’t err—it produced a plausible but nonsensical creation based on its input data and generative process. Hallucinations and Human Perception This distinction is crucial because calling these outputs “errors” could mislead people into thinking that LLMs are making simple mistakes that can be fixed with better logic or more data. But hallucinations in LLMs are not bugs that can be patched. They are a byproduct of how these models work—of generating text without a built-in sense of truth. The onus is still on the human user to guide the AI’s output by crafting better prompts, setting clearer parameters, and using post-processing tools to verify facts. This is why the term “hallucination,” while imperfect, is closer to the mark. It conveys that the model is not just producing an error but fabricating new content—fabrications that are a natural consequence of its design, not the result of poor logic or faulty inputs. It serves as a reminder that these models are generative, not analytical. They don’t have a grasp of reality and can produce completely fabricated content even when all the inputs seem perfect. Setting Expectations for AI’s Outputs Ultimately, the data scientist’s argument comes from a place of wanting to simplify AI’s behaviors for the end-user. If we call these outputs “errors,” maybe people will understand AI’s limitations better. But in reality, this simplification does a disservice to the complexity of these models. We need to help people understand that AI models do not think, reason, or understand—they predict and generate. Their hallucinations are not “errors” in a mechanical or statistical sense but are intrinsic artifacts of how they operate. Until we develop AI models with built-in mechanisms for validating truth, we will continue to see outputs that are not just factually wrong but sometimes fantastical. And as we refine our language and expectations around AI, we need to keep terms like “hallucination” in place—if only to remind ourselves that these models are not yet capable of true understanding. So, while I appreciate the sentiment behind labeling these outputs as errors, it inadvertently strips away the nuances that make AI hallucinations fundamentally different from the statistical errors many data scientists are familiar with. As we continue to refine our models and our language, it’s worth keeping these distinctions in mind to set clearer expectations for what AI can and cannot do. About Me: 25+ year IT veteran combining data, AI, risk management, strategy, and education. 4x hackathon winner and social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com About Me: 25+ year IT veteran combining data, AI, risk management, strategy, and education. 4x hackathon winner and social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com

Why Your Data Scientists Will Struggle With AI Hallucinations

It’s a cycle we’ve seen play out countless times: someone asks a large language model (LLM) a factual question, receives a confident but incorrect answer, and immediately cries foul. “These AI systems can’t be trusted!” “They’re unreliable!” “Look at how it just made things up!” The internet erupts with critics waving the banner of AI’s imperfections, deriding the technology for being riddled with “hallucinations” and fabricating details with the audacity of an overzealous storyteller. But here’s the thing: large language models were never meant to be sources of absolute truth. Yet, we continue to treat them as such, using them like search engines or digital encyclopedias, then express shock and dismay when they fall short of our expectations. The truth is, LLMs are incredibly powerful tools for generating language, contextualizing information, and assisting with creative and analytical tasks. But they are not—or at least, not yet—perfect arbiters of fact. If we want to use AI better, it’s time to stop expecting LLMs to perform roles they were never designed for and start leveraging them for what they’re truly good at: aiding human creativity, providing context, and generating possibilities—not absolute truths. Let’s break down why this misconception persists and how we can realign our expectations to get the most out of these models. Understanding the Nature of LLMs: Statistical, Not Factual The root of the issue lies in a misunderstanding of what LLMs actually do. Large language models, like GPT-4, are statistical machines at their core. They don’t “know” facts the way humans do. Instead, they predict the most likely sequence of words based on the patterns in the vast amounts of text they’ve been trained on. When you ask an LLM a question, it doesn’t search a database of verified truths. It generates a response based on its understanding of language patterns, which may or may not align with reality. This is why LLMs are prone to what’s known as “hallucination”—a term used to describe when the model outputs information that sounds plausible but is factually incorrect or entirely fabricated. Hallucinations happen because the model’s objective is not to verify facts but to produce fluent, coherent, and contextually appropriate text. The more coherent it sounds, the more likely it is to be seen as “true,” even when it’s not. Expecting an LLM to consistently generate factually accurate information is like expecting a skilled fiction writer to suddenly become a historian. Just because the prose flows beautifully doesn’t mean the content is accurate. When we treat LLMs as authoritative sources, we’re misusing them—and we set ourselves up for disappointment. The Problem Isn’t AI Hallucinations—It’s Misaligned Expectations Critics are quick to pounce on AI hallucinations as proof that LLMs are fundamentally flawed. But this criticism misses the point. The problem isn’t that the models generate incorrect information; it’s that we’re using them in ways that demand factual accuracy. We’re holding AI to a standard it was never designed to meet. Imagine you have a calculator. You wouldn’t ask it to compose a poem and then get frustrated when it spits out a bunch of numbers. That’s not what it’s for. Similarly, asking an LLM to be a definitive source of truth is a misuse of the tool. It’s designed to help us with language-related tasks, like generating ideas, drafting content, or answering questions in a conversational manner—not to be a substitute for fact-checking. If you need a reliable source of factual information, that’s what databases, search engines, and encyclopedias are for. LLMs can assist in synthesizing information or providing context, but they should be used with the understanding that their responses might not always be correct. Just as we double-check a human’s work, we should verify the outputs of AI models. Why Do People Keep Using LLMs This Way? So, why do people keep using LLMs as if they were digital oracles of truth? Part of the reason is that LLMs sound so convincing. They generate language with a fluency that mimics human expertise, often complete with references, citations, and confident assertions. This creates an illusion of authority, leading users to overestimate the model’s reliability. When an LLM generates an incorrect or fictionalized response, it feels like a betrayal, even though the model is just doing what it was programmed to do—producing language, not truth. Another reason is convenience. It’s tempting to use LLMs as a one-stop shop for answers. They’re fast, accessible, and capable of covering a wide range of topics. But convenience shouldn’t come at the cost of accuracy. Using LLMs for quick answers without verification is like skimming Wikipedia and assuming every word is 100% accurate without cross-referencing any sources. The burden of truth remains on the user. Using LLMs More Effectively: Playing to Their Strengths To use LLMs better, we need to play to their strengths. Here’s how: Creative and Analytical Assistance: LLMs are excellent at generating ideas, brainstorming, and exploring possibilities. If you’re a writer stuck in a rut, an AI can suggest plot twists, character backstories, or article structures. If you’re an entrepreneur developing a new product, an AI can help you articulate your vision, consider new angles, and refine your messaging.
Contextual Understanding: While LLMs may not be sources of truth, they can help contextualize information. They can explain concepts in simpler terms, summarize complex articles, or engage in hypothetical scenarios to explore potential outcomes. This can be incredibly useful for making sense of overwhelming amounts of information or sparking new ways of thinking.
Drafting and Editing: AI can generate first drafts or assist in editing, helping human creators focus on refining rather than starting from scratch. It can speed up content creation processes by handling mundane drafting tasks, allowing humans to apply their expertise in finalizing and polishing the content.
Language and Communication: LLMs can be invaluable for generating responses, crafting emails, or composing speeches. They can be trained to match specific tones or styles, making them useful tools for content that requires a human touch but doesn’t need to be fact-checked line-by-line. Integrating AI With Human Oversight The key to using LLMs effectively is to integrate them into workflows that include human oversight. This means verifying facts, cross-referencing sources, and using the AI’s outputs as starting points rather than final products. It’s about using AI as a collaborator, not a replacement for human judgment. Imagine LLMs as highly capable assistants. They’re knowledgeable, articulate, and quick, but they still need a manager (you) to provide direction, verify their work, and ensure quality. This kind of relationship leverages the strengths of both humans and machines, producing better results than either could achieve alone. Building Better AI Literacy Ultimately, the solution to the LLM-as-source-of-truth problem is better AI literacy. Users need to understand what these models are and what they aren’t. They need to be educated about the limitations of AI and the importance of critical thinking when interacting with machine-generated content. Organizations developing LLMs also have a role to play. Clearer disclaimers, transparency about the model’s limitations, and even built-in fact-checking mechanisms could help set expectations and guide users toward better practices. The goal should be to foster a realistic understanding of what AI can do and how it should be used—because, when used correctly, LLMs can be incredibly powerful allies in navigating information, creativity, and communication. Let’s Use AI for What It’s Good At It’s time to stop treating LLMs as fact machines and start seeing them for what they truly are: advanced tools for generating language, aiding creativity, and providing context. They’re not replacements for human expertise or definitive sources of truth, and they shouldn’t be judged as such. If we can shift our mindset and use LLMs in ways that align with their design and capabilities, we’ll stop getting frustrated by their hallucinations and start appreciating their real value. Let’s use AI better, not as an oracle, but as a partner—one that helps us create, explore, and communicate more effectively while leaving the job of truth-seeking and validation where it belongs: with us. About Me: 20+ year veteran combining data, AI, risk management, strategy, and education. Social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com It’s a cycle we’ve seen play out countless times: someone asks a large language model (LLM) a factual question, receives a confident but incorrect answer, and immediately cries foul. “These AI systems can’t be trusted!” “They’re unreliable!” “Look at how it just made things up!” The internet erupts with critics waving the banner of AI’s imperfections, deriding the technology for being riddled with “hallucinations” and fabricating details with the audacity of an overzealous storyteller. But here’s the thing: large language models were never meant to be sources of absolute truth. Yet, we continue to treat them as such, using them like search engines or digital encyclopedias, then express shock and dismay when they fall short of our expectations. The truth is, LLMs are incredibly powerful tools for generating language, contextualizing information, and assisting with creative and analytical tasks. But they are not—or at least, not yet—perfect arbiters of fact. If we want to use AI better, it’s time to stop expecting LLMs to perform roles they were never designed for and start leveraging them for what they’re truly good at: aiding human creativity, providing context, and generating possibilities—not absolute truths. Let’s break down why this misconception persists and how we can realign our expectations to get the most out of these models. Understanding the Nature of LLMs: Statistical, Not Factual The root of the issue lies in a misunderstanding of what LLMs actually do. Large language models, like GPT-4, are statistical machines at their core. They don’t “know” facts the way humans do. Instead, they predict the most likely sequence of words based on the patterns in the vast amounts of text they’ve been trained on. When you ask an LLM a question, it doesn’t search a database of verified truths. It generates a response based on its understanding of language patterns, which may or may not align with reality. This is why LLMs are prone to what’s known as “hallucination”—a term used to describe when the model outputs information that sounds plausible but is factually incorrect or entirely fabricated. Hallucinations happen because the model’s objective is not to verify facts but to produce fluent, coherent, and contextually appropriate text. The more coherent it sounds, the more likely it is to be seen as “true,” even when it’s not. Expecting an LLM to consistently generate factually accurate information is like expecting a skilled fiction writer to suddenly become a historian. Just because the prose flows beautifully doesn’t mean the content is accurate. When we treat LLMs as authoritative sources, we’re misusing them—and we set ourselves up for disappointment. The Problem Isn’t AI Hallucinations—It’s Misaligned Expectations Critics are quick to pounce on AI hallucinations as proof that LLMs are fundamentally flawed. But this criticism misses the point. The problem isn’t that the models generate incorrect information; it’s that we’re using them in ways that demand factual accuracy. We’re holding AI to a standard it was never designed to meet. Imagine you have a calculator. You wouldn’t ask it to compose a poem and then get frustrated when it spits out a bunch of numbers. That’s not what it’s for. Similarly, asking an LLM to be a definitive source of truth is a misuse of the tool. It’s designed to help us with language-related tasks, like generating ideas, drafting content, or answering questions in a conversational manner—not to be a substitute for fact-checking. If you need a reliable source of factual information, that’s what databases, search engines, and encyclopedias are for. LLMs can assist in synthesizing information or providing context, but they should be used with the understanding that their responses might not always be correct. Just as we double-check a human’s work, we should verify the outputs of AI models. Why Do People Keep Using LLMs This Way? So, why do people keep using LLMs as if they were digital oracles of truth? Part of the reason is that LLMs sound so convincing. They generate language with a fluency that mimics human expertise, often complete with references, citations, and confident assertions. This creates an illusion of authority, leading users to overestimate the model’s reliability. When an LLM generates an incorrect or fictionalized response, it feels like a betrayal, even though the model is just doing what it was programmed to do—producing language, not truth. Another reason is convenience. It’s tempting to use LLMs as a one-stop shop for answers. They’re fast, accessible, and capable of covering a wide range of topics. But convenience shouldn’t come at the cost of accuracy. Using LLMs for quick answers without verification is like skimming Wikipedia and assuming every word is 100% accurate without cross-referencing any sources. The burden of truth remains on the user. Using LLMs More Effectively: Playing to Their Strengths To use LLMs better, we need to play to their strengths. Here’s how: Creative and Analytical Assistance: LLMs are excellent at generating ideas, brainstorming, and exploring possibilities. If you’re a writer stuck in a rut, an AI can suggest plot twists, character backstories, or article structures. If you’re an entrepreneur developing a new product, an AI can help you articulate your vision, consider new angles, and refine your messaging. Contextual Understanding: While LLMs may not be sources of truth, they can help contextualize information. They can explain concepts in simpler terms, summarize complex articles, or engage in hypothetical scenarios to explore potential outcomes. This can be incredibly useful for making sense of overwhelming amounts of information or sparking new ways of thinking. Drafting and Editing: AI can generate first drafts or assist in editing, helping human creators focus on refining rather than starting from scratch. It can speed up content creation processes by handling mundane drafting tasks, allowing humans to apply their expertise in finalizing and polishing the content. Language and Communication: LLMs can be invaluable for generating responses, crafting emails, or composing speeches. They can be trained to match specific tones or styles, making them useful tools for content that requires a human touch but doesn’t need to be fact-checked line-by-line. Creative and Analytical Assistance : LLMs are excellent at generating ideas, brainstorming, and exploring possibilities. If you’re a writer stuck in a rut, an AI can suggest plot twists, character backstories, or article structures. If you’re an entrepreneur developing a new product, an AI can help you articulate your vision, consider new angles, and refine your messaging. Creative and Analytical Assistance Contextual Understanding : While LLMs may not be sources of truth, they can help contextualize information. They can explain concepts in simpler terms, summarize complex articles, or engage in hypothetical scenarios to explore potential outcomes. This can be incredibly useful for making sense of overwhelming amounts of information or sparking new ways of thinking. Contextual Understanding Drafting and Editing : AI can generate first drafts or assist in editing, helping human creators focus on refining rather than starting from scratch. It can speed up content creation processes by handling mundane drafting tasks, allowing humans to apply their expertise in finalizing and polishing the content. Drafting and Editing Language and Communication : LLMs can be invaluable for generating responses, crafting emails, or composing speeches. They can be trained to match specific tones or styles, making them useful tools for content that requires a human touch but doesn’t need to be fact-checked line-by-line. Language and Communication Integrating AI With Human Oversight The key to using LLMs effectively is to integrate them into workflows that include human oversight. This means verifying facts, cross-referencing sources, and using the AI’s outputs as starting points rather than final products. It’s about using AI as a collaborator, not a replacement for human judgment. Imagine LLMs as highly capable assistants. They’re knowledgeable, articulate, and quick, but they still need a manager (you) to provide direction, verify their work, and ensure quality. This kind of relationship leverages the strengths of both humans and machines, producing better results than either could achieve alone. Building Better AI Literacy Ultimately, the solution to the LLM-as-source-of-truth problem is better AI literacy. Users need to understand what these models are and what they aren’t. They need to be educated about the limitations of AI and the importance of critical thinking when interacting with machine-generated content. Organizations developing LLMs also have a role to play. Clearer disclaimers, transparency about the model’s limitations, and even built-in fact-checking mechanisms could help set expectations and guide users toward better practices. The goal should be to foster a realistic understanding of what AI can do and how it should be used—because, when used correctly, LLMs can be incredibly powerful allies in navigating information, creativity, and communication. Let’s Use AI for What It’s Good At It’s time to stop treating LLMs as fact machines and start seeing them for what they truly are: advanced tools for generating language, aiding creativity, and providing context. They’re not replacements for human expertise or definitive sources of truth, and they shouldn’t be judged as such. If we can shift our mindset and use LLMs in ways that align with their design and capabilities, we’ll stop getting frustrated by their hallucinations and start appreciating their real value. Let’s use AI better, not as an oracle, but as a partner—one that helps us create, explore, and communicate more effectively while leaving the job of truth-seeking and validation where it belongs: with us. About Me: 20+ year veteran combining data, AI, risk management, strategy, and education. Social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com About Me: 20+ year veteran combining data, AI, risk management, strategy, and education. Social impact from data advocate. Currently working to jumpstart the AI workforce in the Philippines. Learn more about me here: https://docligot.com

Hallucinations Are A Feature of AI, Humans Are The Bug

Authors:
(1) Zhan Ling, UC San Diego and equal contribution;
(2) Yunhao Fang, UC San Diego and equal contribution;
(3) Xuanlin Li, UC San Diego;
(4) Zhiao Huang, UC San Diego;
(5) Mingu Lee, Qualcomm AI Research and Qualcomm AI Research
(6) Roland Memisevic, Qualcomm AI Research;
(7) Hao Su, UC San Diego. Table of Links Abstract and Introduction Related work Motivation and Problem Formulation Deductively Verifiable Chain-of-Thought Reasoning Experiments Limitations Conclusion, Acknowledgements and References A Deductive Verification with Vicuna Models B More Discussion on Improvements of Deductive Verification Accuracy Versus Improvements on Final Answer Correctness C More Details on Answer Extraction D Prompts E More Deductive Verification Examples 2 Related work Reasoning with large language models. Recent large language models (LLMs) [3, 8, 57, 47, 38, 18, 9, 37] have shown incredible ability in solving complex reasoning tasks. Instead of letting LLMs directly generate final answers as output, prior work have shown that by encouraging step-by-step reasoning through proper prompting, such as Chain-of-Thought (CoT) prompting [50] and many others [21, 59, 58, 44, 48, 60, 25, 54], LLMs exhibit significantly better performance across diverse reasoning tasks. To further improve the step-by-step reasoning process, some recent studies have investigated leveraging external solvers such as program interpreters [39, 5, 27], training and calling external reasoning modules [11], or performing explicit search to generate deductive steps [2, 46]. Parallel to these works, we do not rely on external modules and algorithms, and we directly leverage the in-context learning ability of LLMs to generate more precise and rigorous deductive reasonings. Large language models as verifiers. Using language models to evaluate model generations has been a long standing idea [22, 36, 40, 4]. As LLMs exhibit impressive capabilities across diverse tasks, it becomes a natural idea to use LLMs as evaluation and verification tools. For example, [10, 11, 33] finetune LLMs to verify solutions and intermediate steps. LLMs aligned with RLHF [32, 31, 48] have also been employed to compare different model generations. In addition, recent works like [43, 52, 28, 6] leverage prompt designs to allow LLMs to self-verify, self-refine, and self-debug without the need for finetuning. However, these works do not focus on the rigor and trustworthiness of the deductive reasoning processes at every reasoning step. In this work, we propose a natural language-based deductive reasoning format that allows LLMs to self-verify every intermediate step of a deductive reasoning process, thereby improving the rigor and trustfulness of reasoning. Additionally, while some recent works [12, 53, 15, 34] have proposed methods to verify individual steps in a reasoning process, our approach distinguishes from these works in the following perspectives: (1) Our approach leverages in-context learning to achieve reasoning verification, without the need for language model finetuning. (2) Our Natural Program-based LLM verification approach not only identifies invalid reasoning steps, but also provides explicit explanations for why they are invalid, detailing the specific reasoning errors involved. (3) Our Natural Program-based reasoning and verification approach is compatible with in-context abstract reasoning tasks where reasoning steps do not possess proof-like entailment structures. For example, our approach is compatible with the Last Letters task, where the LLM is instructed to output the concatenation of the last letters of all words in a sequence as the final answer. (4) Our Natural Program approach allows the use of commonsense knowledge not explicitly listed in premises. For example, consider this problem: “Marin eats 4 apples a day. How many apples does he eat in November?” Even though “November has 30 days” is not explicitly listed in the premises, Natural Program permits the use of such common knowledge within a reasoning step. Our in-context verification process is also capable of handling these implicit premises (e.g., if LLM outputs “November has 29 days” in a reasoning step, it will be marked as invalid). This paper is available on arxiv under CC BY 4.0 DEED license. Authors: (1) Zhan Ling, UC San Diego and equal contribution; (2) Yunhao Fang, UC San Diego and equal contribution; (3) Xuanlin Li, UC San Diego; (4) Zhiao Huang, UC San Diego; (5) Mingu Lee, Qualcomm AI Research and Qualcomm AI Research (6) Roland Memisevic, Qualcomm AI Research; (7) Hao Su, UC San Diego. Authors: Authors: (1) Zhan Ling, UC San Diego and equal contribution; (2) Yunhao Fang, UC San Diego and equal contribution; (3) Xuanlin Li, UC San Diego; (4) Zhiao Huang, UC San Diego; (5) Mingu Lee, Qualcomm AI Research and Qualcomm AI Research (6) Roland Memisevic, Qualcomm AI Research; (7) Hao Su, UC San Diego. Table of Links Abstract and Introduction Abstract and Introduction Related work Related work Motivation and Problem Formulation Motivation and Problem Formulation Deductively Verifiable Chain-of-Thought Reasoning Deductively Verifiable Chain-of-Thought Reasoning Experiments Experiments Limitations Limitations Conclusion, Acknowledgements and References Conclusion, Acknowledgements and References A Deductive Verification with Vicuna Models A Deductive Verification with Vicuna Models B More Discussion on Improvements of Deductive Verification Accuracy Versus Improvements on Final Answer Correctness B More Discussion on Improvements of Deductive Verification Accuracy Versus Improvements on Final Answer Correctness C More Details on Answer Extraction C More Details on Answer Extraction D Prompts D Prompts E More Deductive Verification Examples E More Deductive Verification Examples 2 Related work Reasoning with large language models. Recent large language models (LLMs) [3, 8, 57, 47, 38, 18, 9, 37] have shown incredible ability in solving complex reasoning tasks. Instead of letting LLMs directly generate final answers as output, prior work have shown that by encouraging step-by-step reasoning through proper prompting, such as Chain-of-Thought (CoT) prompting [50] and many others [21, 59, 58, 44, 48, 60, 25, 54], LLMs exhibit significantly better performance across diverse reasoning tasks. To further improve the step-by-step reasoning process, some recent studies have investigated leveraging external solvers such as program interpreters [39, 5, 27], training and calling external reasoning modules [11], or performing explicit search to generate deductive steps [2, 46]. Parallel to these works, we do not rely on external modules and algorithms, and we directly leverage the in-context learning ability of LLMs to generate more precise and rigorous deductive reasonings. Reasoning with large language models. Large language models as verifiers. Using language models to evaluate model generations has been a long standing idea [22, 36, 40, 4]. As LLMs exhibit impressive capabilities across diverse tasks, it becomes a natural idea to use LLMs as evaluation and verification tools. For example, [10, 11, 33] finetune LLMs to verify solutions and intermediate steps. LLMs aligned with RLHF [32, 31, 48] have also been employed to compare different model generations. In addition, recent works like [43, 52, 28, 6] leverage prompt designs to allow LLMs to self-verify, self-refine, and self-debug without the need for finetuning. However, these works do not focus on the rigor and trustworthiness of the deductive reasoning processes at every reasoning step. In this work, we propose a natural language-based deductive reasoning format that allows LLMs to self-verify every intermediate step of a deductive reasoning process, thereby improving the rigor and trustfulness of reasoning. Large language models as verifiers. Additionally, while some recent works [12, 53, 15, 34] have proposed methods to verify individual steps in a reasoning process, our approach distinguishes from these works in the following perspectives: (1) Our approach leverages in-context learning to achieve reasoning verification, without the need for language model finetuning. (2) Our Natural Program-based LLM verification approach not only identifies invalid reasoning steps, but also provides explicit explanations for why they are invalid, detailing the specific reasoning errors involved. (3) Our Natural Program-based reasoning and verification approach is compatible with in-context abstract reasoning tasks where reasoning steps do not possess proof-like entailment structures. For example, our approach is compatible with the Last Letters task, where the LLM is instructed to output the concatenation of the last letters of all words in a sequence as the final answer. (4) Our Natural Program approach allows the use of commonsense knowledge not explicitly listed in premises. For example, consider this problem: “Marin eats 4 apples a day. How many apples does he eat in November?” Even though “November has 30 days” is not explicitly listed in the premises, Natural Program permits the use of such common knowledge within a reasoning step. Our in-context verification process is also capable of handling these implicit premises (e.g., if LLM outputs “November has 29 days” in a reasoning step, it will be marked as invalid). (1) (2) (3) (4) This paper is available on arxiv under CC BY 4.0 DEED license. This paper is available on arxiv under CC BY 4.0 DEED license. available on arxiv

Stories, News & Mentions about HAL

Hal’s Stories on HackerNoon

Hal's News & Mentions