Compared to manufacturing, knowledge work productivity is stuck in the stone age

F-ONE Group

In this article, you will learn a couple of Machine Learning-Based Approaches for Anomaly Detection and then show how to apply one of these approaches to solve a specific use case for anomaly detection (Credit Fraud detection) in part two. A common need when you analyzing real-world data-sets is determining which data point stand out as being different from all other data points. Such data points are known as , and the goal of anomaly detection (also known as outlier detection) is to determine all such data points in a data-driven fashion. can be caused by errors in the data but sometimes are indicative of a new, previously unknown, underlying process. anomalies Anomalies What is Anomaly Detection? Anomaly detection is a technique used to identify unusual patterns that do not conform to expected behavior. It can be considered the thoughtful process of determining what is normal and what is not. are also referred to as outliers, novelties, noise, exceptions and deviations. Anomalies Let’s take an example from students in the classrooms to understand what Anomalies or outliers real means. Students always perform differently; some students either outperform other students or failed to even pass with a minimum when it comes to securing marks in subjects. An example most of the students scored between 40% up to 80%, we can say these marks are generally normally distributed. But if a student gets a score that is extremely high(99% ) or extremely low ( 5%) in statistics and others, related areas like machine learning these values are referred to as Anomalies or Outliers. Simply, anomaly detection is the task of defining a boundary around normal data points so that they can be distinguishable from outliers. How do we identify whether data points are normal or anomalous? In some simple cases, as in the example figure below, can give us valuable information. data visualization Figure One In the above figure, I show you what it’s like to be within a set of closely related data-points. From the figure above you can identify what is a normal data point and what is not a normal data point. The data point with is the anomaly or outlier because it deviates hugely from the normal data points(data point with ). outliers red color blue color Applications of Anomaly Detection in the Business world. Anomaly detection is applicable in a variety of domains such as Intrusion detection, for example, identifies strange patterns in the network traffic (that could signal a hack). Health monitoring system in the hospital. Fraud detection in credit card transactions in Banks. Fault detection in operating environments. Detection of fake news and misinformation on the Internet. Industry damage detection. Security and surveillance. “Outliers are not necessarily a bad thing. These are just observations that are not following the same pattern as the other ones. But it can be the case that an outlier is very interesting. For example, if in a biological experiment, a rat is not dead whereas all others are, then it would be very interesting to understand why. This could lead to new scientific discoveries. So, it is important to detect outliers.” – Pierre Lafaye de Micheaux, Author and Statistician Anomalies can be broadly categorized as: a) Point Anomalies: A single instance of data is anomalous if it deviates largely from the rest of the data points. An example is Detecting credit card fraud based on “amount spent.” b) Contextual Anomalies: The abnormality is context-specific because to identify if is the anomaly it depends on contextual information. This type of anomaly is common in time-series data. for example, people spend a lot amount of money during the holiday, but otherwise, it can be different. c) Collective Anomalies: If a collection of related data instances is anomalous with respect to the entire dataset, but not individual values. Example Someone is trying to copy data from a remote machine to a local host unexpectedly( a potential cyber attack). Machine Learning-Based Approaches for Anomaly Detection: Let's learning different approaches we can use in machine learning for anomaly detection. (a) Clustering-Based Anomaly Detection The approach focus on unsupervised learning, similar data points tend to belong to similar groups or clusters, as determined by their distance from local centroids. The k-means algorithm can be used which partition the dataset into a given number of clusters. Any data points that fall outside of these clusters are considered as anomalies. (b) Density-based anomaly detection This approach is based on the K-nearest neighbors algorithm. It’s evident that normal data points always occur around a dense neighborhood and abnormalities deviate far away. To measure the nearest set of a data point, you can use Euclidian distance or a similar measure according to the type of data you have. (c) Support Vector Machine-Based Anomaly Detection A support vector machine is another effective technique for detecting anomalies. One-Class SVMs have been devised for cases in which one class only is known, and the problem is to identify anything outside this class. This is known as novelty detection, and it refers to the automatic identification of unforeseen or abnormal phenomena, i.e. outliers, embedded in a large amount of normal data. (d) Supervised Deep Anomaly Detection In deep learning Supervised deep anomaly detection involves training a deep supervised binary or multi-class classifier, using labels of both normal and anomalous data instances. For instance supervised Deep anomaly detection models, formulated as multi-class classifiers aid in detecting rare brands, prohibited drug name mention and fraudulent health-care transactions. (e) Semi-supervised deep anomaly detection This is a more popular method than supervised DAD, the labels of normal instances are far easier to obtain than anomalies, as a result, semi-supervised DAD techniques are more widely adopted, these techniques leverage existing labels of single (normally positive class) to separate outliers. (f) One-Class Neural Networks (OC-NN) The One class neural network (OC-NN) methods are inspired by kernel-based one-class classification which combines the ability of deep networks to extract a progressively rich representation of data with the one-class objective of creating a tight envelope around normal data. In the future, I will share the second part of this article on how to implement one of the machine learning-based approaches for anomaly detection. What impact do you think Anomaly detection will have on the various industries? I would love to hear your thoughts in the comments below. Useful links and other ML tutorials: http://machinelearningmastery.com/how-to-identify-outliers-in-your-data/ http://www.kdnuggets.com/2017/01/3-methods-deal-outliers.html https://medium.com/the-data-dynasty/anomaly-detection-in-google-analytics-a-new-kind-of-alerting-9c31c13e5237 http://ceur-ws.org/Vol-2289/paper12.pdf 👏👏 you have made it to the end of this article!. I hope you have learned something new that will help you in your career. Congratulations , If you learned something new or enjoyed reading this article, please share it so that others can see it. Until then, see you in the next post! You can also find me on Twitter . @Davis_McDavid Also published at https://davis-david.medium.com/introduction-to-anomaly-detection-using-machine-learning-with-a-case-study-part-one-3fa2ae08f413

These Tips Will Help You Step Up Anomaly Detection Using ML [Part I]

Countries around the world have taken different measures to slow down or stop the spread of the virus. While China, South Korea, and Taiwan quickly dove into AI-powered screening and tracking, western democracies took a more human-driven direction. Almost ten months after the WHO declared the pandemic a global emergency, has one approach proven better than the other? The first case of a person suffering from the COVID-19 virus was reported to the World Health Organization in December 2019. Since then, the pandemic has impacted economic activity worldwide and changed — perhaps permanently, the way we work and communicate with each other. Very few people would have anticipated, earlier this year, that this would become the biggest crisis of our generation, one that would leave an indelible mark on our collective memory. During the last months, we’ve learned more about the virus. We know, now, that the occurs through respiratory droplets when a person coughs, sneezes, speaks, sings, or breathes heavily. The virus can also spread after infected people are in contact with objects such as tables, handrails, or doorknobs. A lot of the COVID-19’s impact has significantly affected . Cities have become hubs for quick transmission of the illness, a process that global travel has only accelerated. transmission of COVID-19 urban centers When first faced with the reality of a rapidly-expanding virus that we knew very little about, the countries of the world began the race to slow down or stop its spread. To do this, different approaches were drawn moderated by regional social and political contexts. In China, South Korea, Taiwan, and Singapore, among others, governments enforced a that incorporated digital technology into healthcare and policy — this approach was based on IoT, big data, and AI. In the Western Democracies, the focus was placed instead on and educating citizens on reducing the danger, especially for those at higher risk through persuasion and consensus. techno-driven approach human capital While the first approach seems to have been proven more effective for identifying, isolating, and quarantining infected people (although, according to a published recently, it also has resulted in citizens’ views being censored), the second (in which people retain agency in the use of technology) might have been too slow to effectively contain the virus. study China had one specific advantage when it comes to surveying and identifying citizens who have been infected with the virus. Most of the Chinese in smart cities has been fone around improving surveillance. In Chongqing alone, there are approximately 2.6 million cameras that monitor 15.35 million people — that’s one camera for every six residents. During the quarantine, the Chinese government even installed CCTV cameras on people’s doors to make sure residents could not leave their houses without authorization. investment The WHO-China Joint Mission has deemed China’s response as “ ”. On the other hand, the Western response has been considered inadequate — with cases rising again and new peaks of infection being reached on a daily basis. As of June this year, South Korea showed a 0.5 death rate per 100,000 people who contracted the virus, while the U.S. had sustained ten times that number. report the most ambitious, agile, and aggressive disease containment in history The Technology Approach Screening, Tracking, and Tracing and have played a significant role in facilitating the tracking of infected and exposed people around the world. While CT scans can take up to 15 minutes to diagnose someone, AI technology can complete the task in just . Artificial intelligence big data 10 seconds During the early days of the pandemic, Chinese authorities decided to use mobile phone applications and payment and social media data to of people that had visited the epicenter of the virus, the Wuhan market (apps like Alipay and WeChat helped with the task). Machine learning models were then applied to analyze transmission dynamics to border checks and surveillance teams. AI was also able to track down citizen’s , while were equipped with cameras to conduct surveillance and issue instructions to not wearing masks or following emergency protocols. Specific technologies were also adopted in Chinese public transportation; for instance, Megvii Technology Limited developed an AI system for metro stations, while Chinese train stations are now actively using thermal scanners to detect infected people and collect their travel history in order to identify other cases. This data is shared with a central server and analyzed using AI in order to supply medical resources. track the movement travel history drones body temperature screening Body temperature detection in Beijing. Image courtesy of Kian Zhang . Since the onset of COVID-19, several other countries have installed high-performance in airports, workplaces, schools, shopping malls, and public transport, facilitating the identification of hotspots of infection. Taiwan began from Wuhan soon after the virus was communicated, comparing a patient’s travel and health histories with immigration records. Although both regions were geographically close, the use of big data has received praise due to the resulting low number of cases and deaths. South Korea also has, since early in the pandemic, implemented using GPS, bank card records, facial recognition, and security camera footage. This detailed following of cases has allowed the country to maintain a very low per-capita mortality rate. infrared thermal cameras testing travelers aggressive contact tracing Diagnosis and Quarantine AI can also help with the rapid of COVID-19. In China, a -assisted service can detect pneumonia cases in just seconds, and can predict the likelihood of infected patients developing acute respiratory distress syndrome and other critical illnesses. And on a global level, an open-source deep convolutional called can detect COVID-19 cases from other diseases of the lung on chest x-rays. detection and diagnosis cloud-based AI machine learning algorithms neural network COVID-Net In addition to technologies specifically developed for dealing with the spread of the virus, are also benefitting from video conferencing and digital monitoring and have been used to successfully treat patients remotely — protecting healthcare workers and allowing family members to participate in treatments. virtual care platforms were imposed early in China. For instance, 15 cities in Hubei were completely locked down from 23rd January. The transport system was suspended in its entirety, and citizens were not allowed to leave their houses. Today, the (QR) Code System acts as a sort of certificate and that tracks movement over a hundred Chinese cities. The system requires an individual to fill out a survey of symptoms and record their temperature so authorities can monitor their movement as they use public transportation or visit a supermarket. Different colors represent low, medium, and high risk, and people with green codes can travel without restrictions (while other colors must isolate for 14 days). Lockdowns Quick Response travel pass In Taiwan, the government has issued for home-quarantined of individuals that use GPS and can trigger messages and fines if the person breaks the isolation. The same has been done in and . electronic monitoring devices South Korea Hong Kong The Human Approach Human rights experts argue that China’s extreme surveillance measures would probably not work in countries where fewer restrictions are imposed. For example, several American states have banned facial recognition, while the 2018 European Union General Data Protection Regulation ensures so that it’s not used against individual . personal data protection freedom and privacy In western democracies, smart cities invested instead in to create consensus and persuasion, and control the transmission of the virus. Instead of accessing citizen’s mobile phones, the governments of Italy and Germany gathered from tracking the concentration and movements of people. When these were not available, governments opted for drive-through testing and apps that ask people to share their data voluntarily. human capital anonymous aggregated data Image courtesy of Kate Trifo . Germany has a that collects pattern data for signs of the virus, while the United Kingdom has actively promoted the use of a smartphone application that uses venue check-in and can alert others when there’s been an infection. In the United States, national studies are capturing through a smartwatch and collecting on clusters of febrile illness — although neither initiatives have been integrated into policy. smartwatch application track and trace resting heart rate real-time data Another measure implemented in the west was the isolation of those infected from others. were put in place not only in affected areas but on a nation-wide level. Yet, “ ”, UK’s Prime Minister claimed. This marks a clear difference with the authoritative regimes that can force the use of smart technologies to address the pandemic and where communities are seen more as of them rather than active participants. Lockdowns no prime minister wants to enact measures like this passive beneficiaries Western democracies had time to plan their crisis management before the cases exited China, however, the dangers of the virus were frequently by American and European governments. According to the aforementioned study, this was due to a combination of decentralized political systems, gaps in governance, and laws of privacy protection. The result was a downplay of the impact of the virus and an accelerated transmission. downplayed “While China has denied the impact of the virus by adopting the means of suppression, the Western democracies have denied by freely sharing the information with their citizens.” Rama Krishna Reddy Kummitha Conclusions This unexpected crisis finds us at the peak of a technological revolution. As Yang Fei, the vice chief of Fuhe town in the Suizhou smart city, stated: “The technology we use today in epidemic control was hard to imagine in the past” ( ). Jie & Quao, 2020, p. 1 In an unprecedented initiative, the Chinese manufacturing industry and technology-based ecosystems were able to assist authorities in fighting COVID-19 using the surveillance infrastructure to impose discipline among its citizens. This strategy seems to have been more successful in stopping the spread of the virus in the region, at least in comparison to the use of technology limited by anonymized data in Western democracies. In large part, this can be also explained by delayed and frequently disorganized initiatives. Both approaches can, I believe, benefit from — in particular, because human mediation is at the center of both approaches. The question is one of distribution of autonomy: How much is given to the government and how much to the citizen. analyzing each other’s successes Iceland was among the first nations to on asymptomatic people using mobile technology and clinic and genome sequencing data. To date, the country has the highest per-capita testing rate and one of the lowest per-capita mortality rates. In order to balance the need for track and trace, European have agreed on not using GPS or a central database, anonymizing data, and retaining it for only 14 days. This is a great example of a type of intervention that takes advantage of advances in technology while keeping privacy a central concern. collect data countries There’s, however, a real concern that the government might take advantage of the changes triggered by the pandemic to reinforce surveillance on citizens even after the virus has been controlled. If governments can ensure that the data they collect will be handled responsibly and for the benefit of society as a whole, if they can guarantee transparency in the collecting and sharing of such data with their citizens and the global community, as well as the ceasing of more restrictive measures once the situation becomes under control, than a merely human-driven one. then a techno-approach is proven to provide better results It’s also worth noting that large areas of the world, as well as groups within high-income countries, don’t have access to the Internet, mobile phones, or smartwatches. and has the potential to amplify socioeconomic inequalities. In order for digital solutions to have a balanced impact on the prevention and treatment of COVID-19, interventions need to be tailored to different regions through subsidies for mobile phone plans, free wi-fi spots, and training programs, among others. Digital health can contribute to disparities in healthcare

Tech VS Human Capital: Chinese and Western Approaches to COVID-19

THE JELLY-BEAN

Thinking as a CEO will help you determine which tasks you need to be doing right now One of the biggest and sneakiest traps that keeps a lot of solopreneurs struggling to attract clients and make money in their service-based businesses is this: They get caught up in doing a lot of the things that make the difference to their bottom line. It’s an easy trap to fall into, especially when you’re just starting out. smallest Until you’re booking enough clients or filling your signature programs and courses so that you have consistent revenue, it can sure feel like you have to do in your business yourself. While it’s true that entrepreneurs wear a lot of hats, a lot of time we heap a lot more on our plates than is necessary. It’s my goal with this article and to help you obliterate overwhelm by dramatically cutting down your to-do list in a way that makes sense for your business and personal life. everything the previous one , I showed you one strategy for knowing exactly where you’re focusing your time, talent and energy for the biggest returns in your solopreneur business. When you use the strategy outlined, you’ll get either an answer of “yes, this is a worthwhile activity” or “no, this isn’t worthwhile for my business”. As a result, your business to-do list should already be significantly shorter. In this previous article Today we’re going to take it up a notch. Plus I’ll help you see how you can afford to outsource certain tasks even if you don’t think you can right now (and why doing so may make or break your business). I’m going to show you how to determine of the tasks you need to do yourself and which ones you can and should outsource. which Have you fallen into a common solopreneur’s trap? Are missing out on booking more clients, making more money and having the kind of business you dream about simply by letting yourself get mired in activities that other people can and should be doing for you? Here’s the truth: a lot of those things you think are critical that you do yourself to book more clients and grow your business probably aren’t. When you think of yourself as “just” a coach, nutritionist, Facebook ads manager or whatever your title is, you can too easily allow yourself to get caught up in serving your clients and the day-to-day administrative tasks that don’t actually result in a steady stream of leads, clients or cash in the bank. A simple litmus test is to track how you spend your average working day and see how much time you’re spending doing activities that: Don’t directly contribute to bringing in new clients Don’t drive sales and bring money in the door Don’t grow your brand/ brand awareness Don’t help you improve your skill set in the areas that help you get more clients, make more sales and grow your brand awareness. But when you take on the role of the “real CEO” of your business, you focus your time, energy and talent on the big vision for your business and on the areas that make the biggest difference to growth and profitability, which are Marketing + Promotion, Sales and Revenue-Generating Programs + Products and Business Development / Personal Skills Acquisition. Now, I know when you’re starting out and before you’ve hit a certain income threshold, you may feel like you can’t afford to outsource. Let me help you shift your thinking around that with a simple exercise that will show you exactly what you should be outsourcing in order to bring in more money. All the other stuff — the daily operations, administration, customer service — can and should be delegated to someone else to do. Here’s what you should outsource in order to bring in more clients and income While there are certain client-getting and income-producing every business owner needs to be doing on a regular basis , the exercise below will help you determine which of the activities in your personal business you can and should outsource now and the dollars-behind-the-reason bottom line. Grab your to-do list and get ready to take a hard look at where you’re investing your time (and where it may be smarter to let someone else do things for you). (you can grab that list here) Step 1: How much is a client worth? How much is one client worth to you and your business? You can take the average amount that a client invests to work with you, whether it’s through individual coaching sessions, a freelance job or through a paid program or course, for example. Write that amount down on a piece of paper. (If you’re just starting out and don’t have any clients yet, you can skip to Step 2.) For example, let’s say you sell a 3-month coaching program for $2000 per client with no other sales. A client is worth about $2000 to you. Step 2: How much is your time worth? How much is your time worth? To make it easy, think of it as dollars per hour, even if how you get paid isn’t according to an hourly wage. For example, if you said in Step 1 that your average client is worth $2000, then divide that amount by the amount of time you invest into that client to come up with your “hourly rate”. Of course, there are some nuances here for services rendered through group programs, individual coaching packages that include more than the sessions and so on, but this will give you a rough idea of what dollar value you’ve placed on your time. To continue with this example, let’s say you spend 10 hours preparing for sessions and working with a client over the 3-month coaching program. Your hourly rat is therefore $200. Step 3: How much will it cost to outsource or delegate certain tasks to someone else? Now take a look at the list of all the things you handle in your business. You’ll need to add in the personal tasks you take care of, too, if you’re a solopreneur and find that you sometimes take time out of your workday to take care of personal to-dos. Which are the activities that you could reasonably hire someone to take care of for you and for less than you determined the value of your time to be in Step 2? (And, like I discussed in , which are the ones you could stop doing altogether?) this article Tasks like uploading and scheduling blog and social media posts, creating graphics, replying to routine inquiries, grocery shopping, housekeeping, bookkeeping and the like may be necessary, but they probably aren’t something you need to handle yourself. Are you seeing that you spend a great deal of your time on $15 per hour activities instead of the ones that directly contribute to you signing up a $2000 client? Circle those items on your list that you should or would like to outsource or delegate to someone else and write a dollar figure of what it would likely cost to hire someone to do each task for you. Step 4: Which tasks should you outsource first? At this point I bet you’re looking at a list of tasks you could outsource for not that big of an investment. But if you have no budget or a very small budget for hiring some help, where do you start? I suggest you start with the easiest task to outsource that will give you the highest return on investment. For many solopreneurs who also take care of many of their household’s day-to-day responsibilities, the best investment may be in a housekeeper or personal shopper who can get the groceries and run errands for you if you find yourself doing these kinds of activities at the expense of your work time. Or your best move might be in a virtual assistant who takes care of many of the administrative tasks that need to be done but which don’t directly bring clients in the door. While having a housekeeper or virtual assistant may seem like an unnecessary luxury or indulgence, they’re not. They’re a smart investment in the success of your business when you use the recouped time wisely. f someone else can reasonably take your place and do the task for you and for less money than your time is worth, you should consider letting someone else handle it for you. Even if you only recoup a few hours a week, when you use those hours to focus on the big income-generating activities in your business, you should see a high return on your investment. Step 5: Which tasks should you prioritize for the biggest returns? Now, what’s left over? What are the tasks that you’ve determined you’ll still be handling and are they the ones that will help you attract and book clients, create income and grow your business quickly? You can download the free to see if you’re focusing your time, talent and energy into the kinds of activities that will make the biggest difference in your business in the shortest amount of time. The activities listed in the checklist help you do three things: attract and book clients, generate income and grow your business. 6-Figure Business Checklist for Coaches, Consultants and Other Service Providers As your business grows and becomes more profitable, you’ll want to re-examine which activities you commit to doing personally instead of outsourcing to someone else. Where can you leverage your time even more? Which activities are truly important for you to handle yourself? Please share your thoughts I’d love to know… What will you stop doing immediately or delegate to others? What business-building activities will you focus on during your recouped time? Wishing you amazing success in your business and life! Originally published at christineparma.com .

Who to Hire First So You Can Get More Clients and Earn More

In nearly all of my recent explorations of Generative AI, I've come to realize how important prompts are. That hasn't necessarily translated me into writing better prompts all the time, but being aware of the problem is at least one step towards correcting it, right? One of the things that I thought would help me personally would be to have a tool to quickly compare and contrast different prompts. Obviously, I could just open up multiple tabs in a browser, but I really wanted something more direct and simplified for my purposes. With that in mind, let me share what I've built. Prompt Tester Prompt Tester is my incredibly imaginatively named tool to... um... test prompts. It begins with one prompt: The idea is that you enter your initial prompt, and then click one or more times to add more prompts. When ready, you can then just click "Generate Results": Before showing some example results, let me talk a bit about how it was built. The Code The backend is an simple Node.js server that handles throwing up the static HTML and responding to the front-end API requests. Once again, I thank Todd Sharp for sharing his initial code with me. Here's the boring simple handling portion: incredibly async function handler(req, res) {
	console.log('Entered handler.', req.method, req.url);

	if(req.method === 'GET' && req.url.indexOf('favicon.ico') === -1) {
		res.writeHead(200, { 'Content-Type':'text/html' });
		res.write(fs.readFileSync('./demo.html'));
		res.end();
	} else if(req.method === 'POST' && req.url === '/api') {

		let body = '';
		req.on('data', chunk => {
			body += chunk.toString();
		});

		req.on('end', async () => {
			body = JSON.parse(body);
			console.log('BODY:\n', JSON.stringify(body, null, '\t'));

			let result = await callGemini(body.prompt);
			res.writeHead(200, { 'Content-Type':'application/json' });
			res.write(JSON.stringify(result));
			res.end();

		});

	}

}

const server = http.createServer(handler);
server.listen(3000);
console.log('Listening on port 3000'); And the part which just passes the prompt off to Google's . In theory, this could be changed to ChatGPT or any other service. callGemini Gemini API const MODEL_NAME = "gemini-pro";
const API_KEY = process.env.GOOGLE_AI_KEY;

const genAI = new GoogleGenerativeAI(API_KEY);
const model = genAI.getGenerativeModel({ model: MODEL_NAME });

async function callGemini(text) {

	const generationConfig = {
		temperature: 0.9,
		topK: 1,
		topP: 1,
		maxOutputTokens: 2048,
	};

	const safetySettings = [
		{ category: HarmCategory.HARM_CATEGORY_HARASSMENT, threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE, },
		{ category: HarmCategory.HARM_CATEGORY_HATE_SPEECH,	threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE, },
		{ category: HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT, threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE, },
		{ category: HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT, threshold: HarmBlockThreshold.BLOCK_MEDIUM_AND_ABOVE, },
	];

	const parts = [
    	{text},
  	];

	const result = await model.generateContent({
		contents: [{ role: "user", parts }],
		generationConfig,
		safetySettings,
	});

	try {

		if(result.response.promptFeedback && result.response.promptFeedback.blockReason) {

			return { error: `Blocked for ${result.response.promptFeedback.blockReason}` };
		}
		const response = result.response.candidates[0].content.parts[0].text;
		return { response };
	} catch(e) {
		// better handling
		return {
			error:e.message
		}
	}
	
} I'm proud to say that I'm now, finally, doing some basic error handling and trying to expose to the user (me) why a prompt was blocked. The front end is relatively simple. I used for the core CSS (again, thank you Todd) and some vanilla JavaScript to handle adding new prompts and making the calls. Here's the HTML (minus the inline CSS): Milligram <h1>Prompt Tester</h1>

<p>
This tool helps you see the result of multiple prompts at the same time. The idea is to use similar prompts with different phrasing 
to see how it impacts the result.
</p>

<div id="prompts">
</div>

<template id="promptRow">
<div class="row">
	<div class="column column-33"><textarea placeholder="Enter your prompt."></textarea></div>
	<div class="column column-67 result"></div>
</div>
<hr>
</template>


<div class="float-right">
<button id="addPrompt">Add Prompt</button> <button id="generateResults">Generate Results</button>
</div> And then the JavaScript. Notice I used above to handle the prompt layout. This is the first time I've used that tag, and it was relatively easy. <template> let $template, $prompts, $addPromptsBtn, $generateResultsBtn;
let promptCount = 0;

document.addEventListener('DOMContentLoaded', init, false);
async function init() {
	
	$addPromptsBtn = document.querySelector('#addPrompt');
	$addPromptsBtn.addEventListener('click',  addPrompt, false);
	$generateResultsBtn = document.querySelector('#generateResults')
	$generateResultsBtn.addEventListener('click',  generateResults, false);
	$template = document.querySelector('#promptRow');
	$prompts = document.querySelector('#prompts');

	addPrompt();
}

function addPrompt() {
	promptCount++;
	const newPrompt = $template.content.cloneNode(true);
	$prompts.append(newPrompt);
}

async function generateResults() {
	// disable add prompt and generate
	$addPromptsBtn.setAttribute('disabled', 'disabled');
	$generateResultsBtn.setAttribute('disabled', 'disabled');

	let $results = document.querySelectorAll('div.result');
	// clear any previous results
	$results.forEach(r => r.innerHTML = '');

	/*
	gather prompts from the inputs
	*/
	let prompts = [];
	let $fields = document.querySelectorAll('#prompts textarea');
	for(f of $fields) prompts.push(f.value);

	let promises = [];
	for(p of prompts) promises.push(getResult(p));
	let results = await Promise.all(promises);

	// assign results to result area for each, handle errors - later
	// there's a one to one correspondance between our array of results and the result div
	for(let i=0;i<results.length;i++) {
		if(results[i].response) $results[i].innerHTML = marked.parse(results[i].response);
		else if(results[i].error) $results[i].innerHTML = `<strong>Error with Prompt: </strong> ${results[i].error}`;
	}

	$addPromptsBtn.removeAttribute('disabled');
	$generateResultsBtn.removeAttribute('disabled');

}

async function getResult(p) {
	console.log('get result for',p);
	// quick return on empty prompt
	if(p.trim() === '') return { response:'<strong>Enter a prompt.</strong>' };
	let req = await fetch('/api', { method:'POST', body: JSON.stringify({prompt:p.trim()})});
	let result = await req.json();
	return result;
} I that's all pretty simple DOM manipulation and API calling, but definitely let me know in a comment below if something doesn't make sense. Notice I fire off all my API calls at once and wait for them to finish. think Promise.all Also, note I use the library. The results from Google typically have Markdown, and this helps render them nicely in my little web app. marked All of this isn't terribly interesting I think, but let's look at some testing. As I said, I the style of prompt was important. Having it presented directly to me in a tool went a of a long way to reinforcing that. knew heck Sample Result - Gravity Let's start with a simple idea - explaining gravity but for different age groups. Because of the large size of the results, I'm going to use a bit of CSS here to help keep things sane. Prompt: explain gravity to me but make it appropriate for a child in 1st grade Gravity is a superpower that our planet has! It's like an invisible force that makes everything on Earth stay on the ground. Imagine you have a ball in your hand. When you drop it, what happens? It falls down, right? That's because of gravity. Gravity pulls the ball towards the center of the Earth, and so it falls to the ground. Gravity is also what keeps us on the ground. It's what keeps our feet planted firmly on the Earth and prevents us from floating away! Gravity is a very important force. It keeps everything in place and helps things work the way they do. Without gravity, we would all be floating around in space, and things would be very chaotic! Here's a fun way to think about gravity: imagine that the Earth is a giant magnet, and everything on Earth is made of metal. The magnet pulls the metal objects towards it, and that's what keeps them on the ground. Gravity is a very important and interesting force. It's one of the things that makes our planet such a unique and special place to live! Prompt: explain gravity to me but make it appropriate for a child in 7th grade Imagine you're playing with a ball. You toss it up in the air, and it comes back down to you. This is because of gravity. Gravity is a force that pulls things toward each other. It's what keeps you on the ground and what makes things fall down. The amount of gravity between two objects depends on their mass. The more mass an object has, the stronger its gravity is. That's why things like planets and stars have more gravity than things like people and cars. Gravity is also what keeps the planets in orbit around the sun. The sun's gravity is much stronger than the Earth's, so it pulls the Earth towards it. This keeps the Earth moving in a circle around the sun. Gravity is a very important force in our universe. It keeps things in place and makes things move. Without gravity, the planets would fly off into space, and we would all float away. Here are some fun facts about gravity: Gravity is responsible for the tides. The moon's gravity pulls on Earth's oceans, causing them to rise and fall. Gravity is the reason why we have an atmosphere. Without gravity, the air would just float away into space. Gravity is what makes it possible for us to walk. When we walk, our feet push against the ground, and the ground pushes back. This is what propels us forward. Gravity is the reason why we don't float away into space. Earth's gravity pulls us towards its center, keeping us on the ground. Note the typo in the prompt below. Gemini handled it just fine. Prompt: explain gravity to me but make it appropriate for a college-aged student Gravity: The Force of Attraction Gravity is a fundamental force in the universe responsible for keeping celestial bodies, such as planets, moons, and stars, in motion. It is also what keeps us firmly planted to the ground and allows objects to fall when dropped. Newton's Law of Universal Gravitation: The law of universal gravitation states that every object in the universe attracts every other object with a force proportional to the product of their masses and inversely proportional to the square of the distance between them. Mathematically, it can be expressed as: F = Gm1m2/r^2 Where: F is the gravitational force between two objects. G is the gravitational constant (6.674 × 10^-11 N m^2/kg^2). m1 and m2 are the masses of the two objects. r is the distance between the centers of the two objects. Significance of Gravity: The gravitational pull of larger celestial bodies keeps smaller ones revolving around them. For example, Earth's gravity keeps the moon in orbit, while Sun's gravity keeps Earth and other planets in their respective orbits. Keeps Celestial Bodies in Orbit: Gravity between the Earth and the moon causes ocean tides. As the moon orbits Earth, its gravitational pull creates a bulge in the ocean's water on the side facing the moon. Another bulge forms on the opposite side of Earth due to the inertial forces. As the Earth rotates, these bulges move across the planet's surface, resulting in high and low tides. Responsible for Tides: Gravity pulls objects towards Earth's center, preventing them from floating away. This phenomenon allows us to walk, stand, and interact with our environment. Keeps Objects on Earth: Gravity plays a crucial role in the formation of stars and galaxies. The gravitational collapse of massive clouds of gas and dust leads to the creation of new stars. Similarly, the gravitational pull of galaxies keeps them bound together, preventing them from dispersing. Formation of Stars and Galaxies: Albert Einstein's general relativity theory provides a more comprehensive understanding of gravity. It explains that gravity is not a force but rather a curvature of spacetime caused by the presence of mass or energy. This curvature affects the motion of objects, causing them to follow curved paths rather than straight lines. Relativity Theory: In conclusion, gravity is a fundamental force responsible for keeping celestial bodies in motion, tides, and the behavior of objects on Earth. It is a complex phenomenon that has been studied extensively over the centuries, and it continues to fascinate scientists and researchers to this day. Sample Result - Pets For my second test, I started with a basic prompt and then a better version that asked for specific types of details: (Quick editorial note - the tabular data below is a bit messy, but was messy in the original output.) not Prompt: why are cats so much better than dogs? Cats and dogs are both popular pets, and there is no definitive answer to the question of which one is better. Both cats and dogs have their own unique set of advantages and disadvantages, and the best pet for you will depend on your individual needs and preferences. Some people prefer cats because they are generally more independent than dogs. Cats are typically happy to entertain themselves, and they don't need to be walked or taken outside for exercise. This can be a big advantage for people who live in apartments or who have busy schedules. Cats are also known for being clean and tidy animals. They groom themselves regularly, and they typically use the litter box without any problems. This can be a big advantage for people who don't want to deal with the mess and smell of a dog. Of course, there are also some disadvantages to having a cat. Cats can be more expensive than dogs, and they can be more difficult to train. Cats are also more likely to scratch furniture and other household items. Ultimately, the decision of whether to get a cat or a dog is a personal one. There is no right or wrong answer, and the best pet for you will depend on your individual needs and preferences. Here is a table summarizing the key differences between cats and dogs: Characteristic Cat Dog Independence More independent Less independent Exercise needs Does not need to be walked or taken outside Needs to be walked or taken outside Cleanliness Cleans itself regularly Needs to be bathed regularly Training Can be difficult to train Easier to train Scratching May scratch furniture and other household items Does not typically scratch furniture Cost More expensive Less expensive Prompt: why are cats so much better than dogs? explain with a bulleted list of reasons that cover emotional well being and financial aspects Emotional well-being: Independence: Cats are more independent than dogs, which can be a good thing for people who want a pet that doesn't require a lot of attention. Low maintenance: Cats are generally lower maintenance than dogs. They don't need to be walked or groomed as often, and they can be left alone for longer periods of time. Quiet: Cats are generally quieter than dogs, which can be ideal for people who live in apartments or have noise-sensitive neighbors. Therapeutic: Studies have shown that cats can have a calming effect on humans, and they can help to reduce stress and anxiety. Financial aspects: Lower cost: Cats are generally less expensive to own than dogs. They eat less food, they need fewer vet visits, and they don't require as much grooming. Easier to travel with: Cats are easier to travel with than dogs. They can be transported in a carrier, and they don't need to be walked or exercised while you're away. Longer lifespan: Cats have a longer lifespan than dogs, on average. This means that you can enjoy your cat's companionship for many years to come. Sample Result - Chain of Thought Prompting The following test came from an presentation from AWS re:Invent: . I found a lot of great advice from this session, including a good overview of Chain of Thought prompting, where the idea is you provide information about the steps used to solve a problem to help the GenAI engine better solve a prompt. excellent AWS re:Invent 2023 - Prompt engineering best practices for LLMs on Amazon Bedrock (AIM377) Now, the example given in that presentation went like so: Q: Roger has 5 tennis balls. he buys 2 more cans of tennis balls. Each 
can has 3 tennis balls. How many tennis balls does he have now?

A: The answer is 11.

Q. The cafeteria had 23 apples. If they used 20 to make lunch and 
bought 6 more, how many apples do they have? In the presentation, the model in use incorrectly returned 27. In my test, it worked correctly, but I absolutely saw issues with math back when I built my last November. generative AI blackjack advice demo As I said, Gemini handled it fine: But in Prompt Tester, I tried the suggested CoT prompt: A: The answer is 9. Q: Roger has 5 tennis balls. he buys 2 more cans of tennis balls. Each 
can has 3 tennis balls. How many tennis balls does he have now?

A: Roger started with 5 balls. 2 cans of 3 tennis balls each is 6 
tennis balls. 5 + 6 = 11. The answer is 11.

Q. The cafeteria had 23 apples. If they used 20 to make lunch and 
bought 6 more, how many apples do they have? And the result was improved, showing how it got to the answer: A: The cafeteria had 23 apples. They used 20 apples for lunch, which 
means they have 3 apples left. They then bought 6 more apples, so 
they now have a total of 3 + 6 = 9 apples.

The answer is 9. The difference is pretty significant. The Code If this seems useful to you at all, feel free to grab the code from here: . As I mentioned, it shouldn't be that difficult to add or some such and use a different service. If you do, let me know! https://github.com/cfjedimaster/ai-testingzone/tree/main/prompt_tester callChatGPT

How to Test Multiple Variations of Generative AI Prompts

জেনারেটিভ এআই প্রম্পটগুলির একাধিক বৈচিত্র কীভাবে পরীক্ষা করবেন

So testen Sie mehrere Variationen generativer KI-Eingabeaufforderungen

Cómo probar múltiples variaciones de indicaciones de IA generativa

Comment tester plusieurs variantes d'invites d'IA générative

जेनरेटिव एआई प्रॉम्प्ट के एकाधिक विविधताओं का परीक्षण कैसे करें

生成 AI プロンプトの複数のバリエーションをテストする方法

Generative AI 프롬프트의 다양한 변형을 테스트하는 방법

Como testar múltiplas variações de prompts de IA generativos

Как протестировать несколько вариантов подсказок генеративного ИИ

Üretken Yapay Zeka İstemlerinin Çoklu Varyasyonlarını Test Etme

Cách kiểm tra nhiều biến thể của lời nhắc AI sáng tạo

如何测试生成式 AI 提示的多种变体

Top 5 Free Courses to Learn Git and Github — Best of Lot One of the important skill for a programmer is to learn and master Git and I have been searching some good tutorials and courses to start with. The Internet is full of git tutorials and a simple Google search will leave you thousands of tutorials but the big question mark is where do you start? It’s easy to pick a tutorial or a blog post if you have some background about what is Git, and how to use it but if you don’t have much background then you need a course which can tell you all the information from the ground up. what it does? I personally like learning from a book or an online course before moving to blog posts as they were often well structured. When you search for Git courses in popular online course websites like Udemy, Pluralsight, or Coursera, you will find some good courses like on Udemy and from Pluralsight which will teach you everything about Git step by step. These are excellent resources to start with Git. Git Complete: The Definitive Guide Git Fundamentals But, some programmers prefer to learn from FREE resources and many of my readers asked me about if I can share some of the good but free git courses they can use to learn Git online by themselves. In this article, I am going to share some of the you can join from your home or office. best free git online courses These are legally free resources, I mean they were made available free by their creators for educational and marketing purpose. If you find that’s not the case then please drop a note and I’ll remove that course. Btw, If you don’t Git, its one of the most popular . distributed source control system You definitely have used other source control software e.g. CVS, SVN, VSS, DFS etc, Git is another one but it’s a little bit different because it’s a , which means you commit changes on your local branch and then push them into remote server (GitHub repository) once you are done. distributed source control system On the other hand, Github is a source code repository i.e. where you can store your source code. In today’s world, a Git repository for programmers is as essential as your Linkedin or Facebook account. That’s the and that’s why I suggest every programmer have their won Github account featuring some of their best code. social proof of being a programmer You should also remember that if you ever have to do a take-home coding test, which many companies nowadays use to screen candidates who are not a , then good coder instead of sending your program into a zip file to them, you better upload into your personal Github repository and send them a link. I have found that many interviewers impressed with this simple act and like to see how you coded the solution with an incremental commit history into Github. The code review is also easy in Github. Remember this tip next time if you have to submit a test code to any company. 5 Online Courses to Learn Git and Github (FREE) Here is a list of some of the best online courses you can join to learn Git and Github for free. These courses provide a good introduction to both Git as version control and overview of essential commands if you want to use Git from command line e.g. push, pull, checkout etc. 1. Git Started with GitHub This course is designed to jump right into showing how Git and GitHub work together, focusing on the Git basic workflow. Students can expect to learn the minimum needed to start using Git in about 30 minutes. You will learn how to set up Git for Windows and Mac OS X and then how to use Git’s help command. After the Installation section, the course walks through the entire Git basic workflow e.g. starting off in GitHub, working locally, and then publishing our changes back to GitHub. In short, this course will teach you the basics of Git and GitHub, with clear, step-by-step instructions by a highly rated teacher. 2. The Ultimate GIT 5-day Challenge This course some basic GIT operations step by step. The course will not dive too deep and takes small steps on each of five days. As you continue through the course, we learn a basic, single-person workflow that could allow anyone to store files at GitHub or BitBucket, two of the popular public Github repositories. If you are looking for some hands-on course to learn Git step by step, this is the for you. You can find this one in , it’s completely free, no coupon needed. right course Udemy This is another git course for beginners. In this course, you will learn how to install Git and configure it for your local environment. 3. Getting Started With Git: Key Concepts for Beginners You will also learn to communicate with local and remote source repositories, add content to a local and remote repository, create comments for your code, understand basic branching and merging and excluding content types from the repository. In short, a good course to learn essential git operations with step by step examples. This course is designed to provide hands-on experience in Git command line on Windows. 4. Command Line Essentials: Git Bash for Windows You will learn key concepts and focus on basics tasks in the in order to be productive quickly. Bash command line In order to use Git on the command line on Windows, you can install GitBash, a tool or software which allows you to access Github from your windows machine. Command Line Essentials: Git Bash for Windows | Udemy Students can expect to learn the minimum needed to start using the Bash shell in less than an hour. The course also contains quizzes, which will help you to retain the knowledge you have learned. In short, a step-by-step guide for Windows users unfamiliar with or the terminal environment. Bash Are you a software developer who wants to get started right now with Git and GitHub? If you’ve heard of Git and GitHub but aren’t sure how to begin, this course takes away the guesswork 5. Short and Sweet: Get Started with Git and GitHub Right Now In just 30 minutes, this “ course covers the essential ideas you need to move forward, without a lot of filler. Short and Sweet” At the end of the course, you’ll be able to set up a GitHub account, install Git, create and configure new Git and , create a change history for your software projects, and publish your software projects to GitHub GitHub repositories That’s all about . You can use these courses to learn and master Git in 2018. some of the best, free Git online courses for programmers If you have not heard of Git before or knows Git little bit, these courses will help you to fill the gaps in your knowledge and mater Git e.g. learning to work with Github, using in Windows etc. command line git client You will also learn some productivity tips along the way to enhance your Git working experience. After finishing these course you better create a Github account if you don’t have already and store some of your best code there. There is no better proof than a good Github repository for your programming skill. This will help you to get your next job. Other you may like to explore: Free Programming Resources 5 Free Spring Framework Courses for Java Developers 5 Online Courses to learn Core Java for Free 5 Online training courses to learn Angular for Free 5 Node JS courses for Java and Web Developers 5 Courses to Learn Big Data and Apache Spark 5 Free Courses to Learn Data Structures and Algorithms 5 Courses to learn Android for Java Developers 5 Free Data Structure and Algorithms Courses for Programmers Closing Notes Thanks for reading this article so far. If you find these free courses useful in learning Git then please share with your friends and colleagues. If you have any questions or feedback then please drop a note. If you like this article, then please share with your friends and colleagues, and don’t forget to follow on Twitter and on Medium! javarevisited javinpaul f you don’t mind spending a bit of money on something worth learning then you can also check on Udemy and from Pluralsight. Two of the most comprehensive courses on Git. P.S. — I GitHub Ultimate: Master Git and GitHub — Beginner to Expert Git Fundamentals

F-ONE GROUP

f-one.group

-- employees

Since n.d.

COMPANY RANKING

F-ONE GROUP

EVERGREEN INDEX #4169

Representing this company? Click here to claim and customize this page!

F-ONE Group WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!

F-ONE GROUP

f-one.group

-- employees

Since n.d.

COMPANY RANKING

F-ONE GROUP

EVERGREEN INDEX #4169

RELATED COMPANIESRANK

STORIES ABOUT F-ONE GROUP

Representing this company? Click here to claim and customize this page!

F-ONE Group WIKI

Apply to get your Tech Company News Page live on HackerNoon.com today!