Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Read by thought-leaders and decision-makers around the world. Phone Number: +1-650-246-9381 Email: pub@towardsai.net
228 Park Avenue South New York, NY 10003 United States
Website: Publisher: https://towardsai.net/#publisher Diversity Policy: https://towardsai.net/about Ethics Policy: https://towardsai.net/about Masthead: https://towardsai.net/about
Name: Towards AI Legal Name: Towards AI, Inc. Description: Towards AI is the world's leading artificial intelligence (AI) and technology publication. Founders: Roberto Iriondo, , Job Title: Co-founder and Advisor Works for: Towards AI, Inc. Follow Roberto: X, LinkedIn, GitHub, Google Scholar, Towards AI Profile, Medium, ML@CMU, FreeCodeCamp, Crunchbase, Bloomberg, Roberto Iriondo, Generative AI Lab, Generative AI Lab Denis Piffaretti, Job Title: Co-founder Works for: Towards AI, Inc. Louie Peters, Job Title: Co-founder Works for: Towards AI, Inc. Louis-François Bouchard, Job Title: Co-founder Works for: Towards AI, Inc. Cover:
Towards AI Cover
Logo:
Towards AI Logo
Areas Served: Worldwide Alternate Name: Towards AI, Inc. Alternate Name: Towards AI Co. Alternate Name: towards ai Alternate Name: towardsai Alternate Name: towards.ai Alternate Name: tai Alternate Name: toward ai Alternate Name: toward.ai Alternate Name: Towards AI, Inc. Alternate Name: towardsai.net Alternate Name: pub.towardsai.net
5 stars – based on 497 reviews

Frequently Used, Contextual References

TODO: Remember to copy unique IDs whenever it needs used. i.e., URL: 304b2e42315e

Resources

Take our 85+ lesson From Beginner to Advanced LLM Developer Certification: From choosing a project to deploying a working product this is the most comprehensive and practical LLM course out there!

Publication

Meet BabyAGI — The Autonomous AI Agent to Streamline Your Tasks
Generative AI   Latest   LLMs   Machine Learning

Meet BabyAGI — The Autonomous AI Agent to Streamline Your Tasks

Last Updated on May 18, 2023 by Editorial Team

Author(s): Sriram Parthasarathy

Originally published on Towards AI.

Explore 10 Task Examples for Utilizing BabyAGI

BabyAGI is an autonomous Artificial Intelligence agent developed by Yohei Nakajima. This autonomous AI agent is designed to generate and execute tasks based on given objectives. It harnesses cutting-edge technologies from OpenAI, Pinecone, LangChain, and Chroma to automate tasks and achieve specific goals. In this blog post, we will dive into the unique features of BabyAGI and explore how it can streamline task automation.

BabyAGI and Project Managers: A Comparison

BabyAGI can be seen as a digital project manager. Just like a project manager, BabyAGI works towards a specific objective by creating a list of tasks, prioritizing, and executing them. It also adapts to changes and makes necessary adjustments to ensure the goal is met.

Like project managers, BabyAGI possesses the ability to learn from previous experiences and make informed decisions.

A Closer Look at BabyAGI

BabyAGI is an AI-driven personal assistant for your computer. By interpreting a given objective, it creates a list of required tasks and then executes them. After each task, BabyAGI evaluates the results and adjusts its approach accordingly.

Unique to BabyAGI is its ability to learn from feedback through trial-and-error, making human-like cognitive decisions. It can also write and run code to achieve specific goals and excels in areas such as cryptocurrency trading, robotics, and autonomous driving.

Using BabyAGI can free up your time to focus on higher-value tasks like decision-making and creative projects.

BabyAGI’s Modus Operandi

BabyAGI follows a systematic approach to automating tasks and making complex decisions:

  • Setting clear Objectives: To begin, the user sets a high-level objective that BabyAGI will accomplish. For example, the objective may be to “Add 1000 Twitter followers in 30 days?”
  • Task Generation (Agent): Next, BabyAGI will use language models such as GPT-4 to break down the objective into a list of potential tasks. These tasks can be research-oriented, such as “Identify and follow Twitter accounts relevant to your niche to increase your visibility and gain new followers”, “Utilize Twitter analytics to track your progress and adjust your strategy accordingly” etc. The list of tasks is then stored in long-term memory (vector database) for future reference.
  • Task Prioritization (Agent): Once there is a list of tasks, BabyAGI will use its reasoning capability to evaluate and prioritize the tasks based on their importance and dependency to achieve the final outcome. It will decide which task to execute first.
  • Task Execution (Agent): BabyAGI will then execute and complete a task. The results of the execution and the information gathered will also be saved in long-term memory for future use.
  • Evaluation & Creating New Tasks: After executing a task, BabyAGI will evaluate the remaining tasks and the results of the previous execution using its reasoning capability. Based on the evaluation, it will create new tasks to be done to achieve the final objective.
  • Repeat: These steps are repeated until BabyAGI achieves the original objective or until the user intervenes. BabyAGI will continually evaluate the progress of the objective and adjust the task list and prioritization accordingly to efficiently reach the desired outcome.
Picture from Yohei Nakajima’s web site

In summary, BabyAGI works by using artificial intelligence to interpret objectives, create a set of tasks, execute them, evaluate the results, and make decisions based on the outcome. It’s a powerful tool that can automate routine tasks and make complex decisions, allowing you to focus on more high-value tasks. The re-prioritization step is a key feature that ensures that BabyAGI is always working towards the objective in the most efficient way possible.

The Pros & Cons of Using BabyAGI

Using BabyAGI to automate tasks has several advantages. Since it can make complex decisions, it can be used for decision-making tasks that require controlling parameters and making complex decisions. This makes it an effective tool for any project that involves identifying tasks based on logical reasoning (To do list type tasks). BabyAGI can also constantly learn feedback from prompts and task results on a trial-and-error basis, which enables it to make human-like cognitive decisions.

While BabyAGI is a powerful tool, it has some limitations. Since it is trained on real-world scenarios and simulated environments, its performance is only as good as the extent of its training data. This makes its usage limited to certain fields. Additionally, BabyAGI does not have access to apps and services available on the internet, which limits its functionality. Please note that this was the case with the original BabyAGI, the latest iteration of BabyAGI implemented on top of Langchain removes this limitation by swapping LLM for execution to Langchain agent.

An Example of BabyAGI in Action

In the past, it has to be a elaborate setup to try and run BabyAGI. Thankfully now we have a web based app we can use. To use BabyAGI, access the web app at https://github.com/miurla/babyagi-ui or the hosted version at babyagi-ui.vercel.app. Input the objective “Add 1000 Twitter followers in 30 days?” and run BabyAGI. BabyAGI UI was created by Yoshiki Miura.

You will need your OpenAPI key, which can be entered in the settings. And remember to limit the number of iterations to save API cost.

Here is an example run of BabyAGI using the web interface at https://babyagi-ui.vercel.app/. Remember that you’ll need to use your OpenAPI key for this process.

Enter the Open API key to run BabyAGI

Here is the start of a new objective to “Add 1000 twitter followers in 30 days?”

Here is the details of the run…

U+1F3AF Objective

Add 1000 twitter followers in 30 days?

U+1F4DD Task List

  1. How to add twitter followers?

U+1F449 Next Task

  1. How to add twitter followers?

U+2705 Task Result

There are several ways to add Twitter followers, including:

  1. Engage with your audience — respond to comments, retweet relevant tweets, and participate in Twitter chats.
  2. Use relevant hashtags to increase the visibility of your tweets.
  3. Share valuable content that is informative or entertaining to your followers.
  4. Run Twitter ads to target specific audiences and increase your reach.
  5. Collaborate with other Twitter users in your niche by retweeting each other’s content and engaging with each other’s followers.

By implementing these strategies consistently over the course of 30 days, you can successfully add 1000 Twitter followers to your account.

Now, BabyAgi will use the new results and the past tasks to generate a list of prioritized tasks as shown below and execute the 1st task in that list. You will see Tags like Generating Tasks, Prioritizing tasks and Executing tasks.

U+1F4DDTask List

  1. Identify and follow Twitter accounts relevant to your niche to increase your visibility and gain new followers
  2. Utilize Twitter analytics to track your progress and adjust your strategy accordingly
  3. Create and share visually appealing graphics and images to increase engagement and attract new followers
  4. Collaborate with influencers or industry leaders in your niche to gain exposure to their followers and increase your own following
  5. Host a Twitter giveaway or contest to incentivize new followers and increase engagement

U+1F449Next Task

  1. Identify and follow Twitter accounts relevant to your niche to increase your visibility and gain new followers

U+2705 Task Result

Understood. To achieve the objective of adding 1000 Twitter followers in 30 days, my task is to identify and follow Twitter accounts that are relevant to the user’s niche. This will help increase their visibility and gain new followers. Based on the previously completed task of how to add Twitter followers, I will use various strategies such as following accounts of industry leaders, engaging with relevant tweets, and using appropriate hashtags to attract new followers. I will also monitor the user’s account regularly to ensure that the number of followers is increasing steadily.

Now, the process continues. BabyAgi will use the new results and the past tasks to generate a list of prioritized tasks as shown below and execute the 1st task in that list. Note that the list of overall tasks have been completed updated between what was initially gnerated and what it has the list of tasks.

U+1F4DDTask List

  1. Conduct a thorough analysis of the user’s niche to identify relevant Twitter accounts that could potentially increase their visibility and attract new followers
  2. Utilize Twitter’s advanced search feature to find tweets and accounts related to the user’s niche and engage with them by liking, retweeting, and commenting on their posts
  3. Use appropriate hashtags in tweets to attract new followers who are interested in the user’s niche
  4. Collaborate with influencers or industry leaders in the user’s niche to gain exposure to their followers and increase their own following
  5. Create and share visually appealing graphics and images to increase engagement and attract new followers
  6. Host a Twitter giveaway or contest to incentivize new followers and increase engagement
  7. Utilize Twitter analytics to track progress and adjust strategy accordingly
  8. Regularly monitor the user’s account to ensure that the number of followers is increasing steadily and adjust the strategy accordingly

Process continues here. 1st task in the above list will get executed and the BabyAgi will use the new results and the past tasks to generate a list of prioritized tasks and execute the 1st task in that list. If you notice the initial task list and each the subsequent task list are very different. It works out well sometimes and in other times it leads to a path where it keeps repeating the same tasks in a loop.

I have said stop after 10 iterations. So it stopped with the following result.

U+2705 Task Result

Based on the user’s target audience and content strategy, I recommend the following schedule for consistent posting on Twitter:

Monday: Share an educational article or blog post related to the user’s industry or niche. Tuesday: Post an inspirational quote or image that resonates with the target audience. Wednesday: Share an informative infographic or video that offers valuable insights or tips. Thursday: Ask a thought-provoking question or conduct a poll to encourage interaction and engagement. Friday: Share a behind-the-scenes glimpse into the user’s business or personal life to humanize the brand. Saturday: Retweet or share content from other thought leaders or influencers in the user’s industry. Sunday: Post a motivational message or call to action that inspires followers to take action.

By posting consistently and providing a mix of valuable content, the user can attract new followers and increase engagement, ultimately leading to the goal of adding 1000 followers in 30 days.

You can see the full run of BabyAGI here for this objective.

I tried this for another objective “Give a detailed weather report for the capital of New York ?” just to illustrate if it can get to latest weather.

You can see the results from this run here. As you can see the list of tasks its generating is good and logical but the results are incorrect as its not looking at the latest weather.

This is something that will get addressed using BabyAGI with Langchain tools. See here the example from Langchain. The execution chain in the original BabyAGI was pure LLM and this has been swapped to Langchain agent so it can access the internet.

Links to try out BabyAGI

BabyAGI : https://github.com/yoheinakajima/babyagi

BabyAGI with Langchain : https://python.langchain.com/en/latest/use_cases/agents/baby_agi_with_agent.html

BabyAGI with Langchain Colab notebook : https://colab.research.google.com/drive/1IzYc6kLzuRMXfUI4aCNxWCYfzZHtdCf-?usp=sharing

BabyAGI UI : to run locally access the web app at https://github.com/miurla/babyagi-ui or the hosted version at babyagi-ui.vercel.app.

Ten examples of where BabyAGI can be used

BabyAGI is a versatile AI tool that can perform a range of tasks, including managing to-do lists, conducting research, and creative writing. For instance, it can assist in generating a list of tasks and prioritizing them to achieve a specific goal. It can also help with product research by analyzing user feedback and market trends. Additionally, BabyAGI can generate ideas for creative writing, such as generating plot-lines, characters, and themes for a novel or screenplay. Its ability to adapt to changes and re-prioritize tasks based on previous outcomes makes it a valuable asset for various industries.

Objectives that involves creating logical tasks are prime candidates for using BabyGPI. Some examples are given below. Remember that as of the current release, BabyGPI cannot leverage internet so all the use cases are restricted to logical reasoning tasks by the LLM. But if you use the one with Langchain integration and provide the serp api key, BabyAGI can connect to the internet and do research as well. I tried many of these but did not let it run to the end (to save on API cost). I have linked those use cases below.

  1. Add 1000 twitter followers in 30 days?
  2. Get 200 Facebook likes on a post in a week.
  3. Increase Pinterest followers by 300 in a month.
  4. Give a detailed weather report for the capital of New York ?
  5. Plan a birthday party at a vegan place in NYC
  6. Come up with 5 AI use cases to use in manufacturing?
  7. What are the top 3 podcast ideas based on latest news?
  8. Find the top 3 braces for handpain?
  9. Create a competitive report for wearable heart rate monitor watch?
  10. What are the top use cases for using Autonomous agents?

As you can see its trending in the right direction to complete these tasks. As technology matures, this will continue to go in the right direction and become very valuable.

Wrapping Up

In conclusion, BabyAGI is an innovative AI tool that automates complex decision-making tasks in various use cases, such as creative writing, research and to-do tasks. It efficiently breaks down high-level objectives into tasks, prioritizes and executes them based on logical reasoning, and continuously evaluates and adjusts its approach.

Leveraging advanced language models like GPT-4, Pinecone, LangChain, and Chroma, BabyAGI can learn from previous tasks and adapt to changing circumstances. Its ability to make complex decisions and control parameters makes it an invaluable asset for automating task management. As AI technology continues to evolve, we can expect even more impressive advancements in the realm of autonomous agents like BabyAGI.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI

Feedback ↓

Sign Up for the Course
`; } else { console.error('Element with id="subscribe" not found within the page with class "home".'); } } }); // Remove duplicate text from articles /* Backup: 09/11/24 function removeDuplicateText() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, strong'); // Select the desired elements const seenTexts = new Set(); // A set to keep track of seen texts const tagCounters = {}; // Object to track instances of each tag elements.forEach(el => { const tagName = el.tagName.toLowerCase(); // Get the tag name (e.g., 'h1', 'h2', etc.) // Initialize a counter for each tag if not already done if (!tagCounters[tagName]) { tagCounters[tagName] = 0; } // Only process the first 10 elements of each tag type if (tagCounters[tagName] >= 2) { return; // Skip if the number of elements exceeds 10 } const text = el.textContent.trim(); // Get the text content const words = text.split(/\s+/); // Split the text into words if (words.length >= 4) { // Ensure at least 4 words const significantPart = words.slice(0, 5).join(' '); // Get first 5 words for matching // Check if the text (not the tag) has been seen before if (seenTexts.has(significantPart)) { // console.log('Duplicate found, removing:', el); // Log duplicate el.remove(); // Remove duplicate element } else { seenTexts.add(significantPart); // Add the text to the set } } tagCounters[tagName]++; // Increment the counter for this tag }); } removeDuplicateText(); */ // Remove duplicate text from articles function removeDuplicateText() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, strong'); // Select the desired elements const seenTexts = new Set(); // A set to keep track of seen texts const tagCounters = {}; // Object to track instances of each tag // List of classes to be excluded const excludedClasses = ['medium-author', 'post-widget-title']; elements.forEach(el => { // Skip elements with any of the excluded classes if (excludedClasses.some(cls => el.classList.contains(cls))) { return; // Skip this element if it has any of the excluded classes } const tagName = el.tagName.toLowerCase(); // Get the tag name (e.g., 'h1', 'h2', etc.) // Initialize a counter for each tag if not already done if (!tagCounters[tagName]) { tagCounters[tagName] = 0; } // Only process the first 10 elements of each tag type if (tagCounters[tagName] >= 10) { return; // Skip if the number of elements exceeds 10 } const text = el.textContent.trim(); // Get the text content const words = text.split(/\s+/); // Split the text into words if (words.length >= 4) { // Ensure at least 4 words const significantPart = words.slice(0, 5).join(' '); // Get first 5 words for matching // Check if the text (not the tag) has been seen before if (seenTexts.has(significantPart)) { // console.log('Duplicate found, removing:', el); // Log duplicate el.remove(); // Remove duplicate element } else { seenTexts.add(significantPart); // Add the text to the set } } tagCounters[tagName]++; // Increment the counter for this tag }); } removeDuplicateText(); //Remove unnecessary text in blog excerpts document.querySelectorAll('.blog p').forEach(function(paragraph) { // Replace the unwanted text pattern for each paragraph paragraph.innerHTML = paragraph.innerHTML .replace(/Author\(s\): [\w\s]+ Originally published on Towards AI\.?/g, '') // Removes 'Author(s): XYZ Originally published on Towards AI' .replace(/This member-only story is on us\. Upgrade to access all of Medium\./g, ''); // Removes 'This member-only story...' }); //Load ionic icons and cache them if ('localStorage' in window && window['localStorage'] !== null) { const cssLink = 'https://code.ionicframework.com/ionicons/2.0.1/css/ionicons.min.css'; const storedCss = localStorage.getItem('ionicons'); if (storedCss) { loadCSS(storedCss); } else { fetch(cssLink).then(response => response.text()).then(css => { localStorage.setItem('ionicons', css); loadCSS(css); }); } } function loadCSS(css) { const style = document.createElement('style'); style.innerHTML = css; document.head.appendChild(style); } //Remove elements from imported content automatically function removeStrongFromHeadings() { const elements = document.querySelectorAll('h1, h2, h3, h4, h5, h6, span'); elements.forEach(el => { const strongTags = el.querySelectorAll('strong'); strongTags.forEach(strongTag => { while (strongTag.firstChild) { strongTag.parentNode.insertBefore(strongTag.firstChild, strongTag); } strongTag.remove(); }); }); } removeStrongFromHeadings(); "use strict"; window.onload = () => { /* //This is an object for each category of subjects and in that there are kewords and link to the keywods let keywordsAndLinks = { //you can add more categories and define their keywords and add a link ds: { keywords: [ //you can add more keywords here they are detected and replaced with achor tag automatically 'data science', 'Data science', 'Data Science', 'data Science', 'DATA SCIENCE', ], //we will replace the linktext with the keyword later on in the code //you can easily change links for each category here //(include class="ml-link" and linktext) link: 'linktext', }, ml: { keywords: [ //Add more keywords 'machine learning', 'Machine learning', 'Machine Learning', 'machine Learning', 'MACHINE LEARNING', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, ai: { keywords: [ 'artificial intelligence', 'Artificial intelligence', 'Artificial Intelligence', 'artificial Intelligence', 'ARTIFICIAL INTELLIGENCE', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, nl: { keywords: [ 'NLP', 'nlp', 'natural language processing', 'Natural Language Processing', 'NATURAL LANGUAGE PROCESSING', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, des: { keywords: [ 'data engineering services', 'Data Engineering Services', 'DATA ENGINEERING SERVICES', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, td: { keywords: [ 'training data', 'Training Data', 'training Data', 'TRAINING DATA', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, ias: { keywords: [ 'image annotation services', 'Image annotation services', 'image Annotation services', 'image annotation Services', 'Image Annotation Services', 'IMAGE ANNOTATION SERVICES', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, l: { keywords: [ 'labeling', 'labelling', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, pbp: { keywords: [ 'previous blog posts', 'previous blog post', 'latest', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, mlc: { keywords: [ 'machine learning course', 'machine learning class', ], //Change your article link (include class="ml-link" and linktext) link: 'linktext', }, }; //Articles to skip let articleIdsToSkip = ['post-2651', 'post-3414', 'post-3540']; //keyword with its related achortag is recieved here along with article id function searchAndReplace(keyword, anchorTag, articleId) { //selects the h3 h4 and p tags that are inside of the article let content = document.querySelector(`#${articleId} .entry-content`); //replaces the "linktext" in achor tag with the keyword that will be searched and replaced let newLink = anchorTag.replace('linktext', keyword); //regular expression to search keyword var re = new RegExp('(' + keyword + ')', 'g'); //this replaces the keywords in h3 h4 and p tags content with achor tag content.innerHTML = content.innerHTML.replace(re, newLink); } function articleFilter(keyword, anchorTag) { //gets all the articles var articles = document.querySelectorAll('article'); //if its zero or less then there are no articles if (articles.length > 0) { for (let x = 0; x < articles.length; x++) { //articles to skip is an array in which there are ids of articles which should not get effected //if the current article's id is also in that array then do not call search and replace with its data if (!articleIdsToSkip.includes(articles[x].id)) { //search and replace is called on articles which should get effected searchAndReplace(keyword, anchorTag, articles[x].id, key); } else { console.log( `Cannot replace the keywords in article with id ${articles[x].id}` ); } } } else { console.log('No articles found.'); } } let key; //not part of script, added for (key in keywordsAndLinks) { //key is the object in keywords and links object i.e ds, ml, ai for (let i = 0; i < keywordsAndLinks[key].keywords.length; i++) { //keywordsAndLinks[key].keywords is the array of keywords for key (ds, ml, ai) //keywordsAndLinks[key].keywords[i] is the keyword and keywordsAndLinks[key].link is the link //keyword and link is sent to searchreplace where it is then replaced using regular expression and replace function articleFilter( keywordsAndLinks[key].keywords[i], keywordsAndLinks[key].link ); } } function cleanLinks() { // (making smal functions is for DRY) this function gets the links and only keeps the first 2 and from the rest removes the anchor tag and replaces it with its text function removeLinks(links) { if (links.length > 1) { for (let i = 2; i < links.length; i++) { links[i].outerHTML = links[i].textContent; } } } //arrays which will contain all the achor tags found with the class (ds-link, ml-link, ailink) in each article inserted using search and replace let dslinks; let mllinks; let ailinks; let nllinks; let deslinks; let tdlinks; let iaslinks; let llinks; let pbplinks; let mlclinks; const content = document.querySelectorAll('article'); //all articles content.forEach((c) => { //to skip the articles with specific ids if (!articleIdsToSkip.includes(c.id)) { //getting all the anchor tags in each article one by one dslinks = document.querySelectorAll(`#${c.id} .entry-content a.ds-link`); mllinks = document.querySelectorAll(`#${c.id} .entry-content a.ml-link`); ailinks = document.querySelectorAll(`#${c.id} .entry-content a.ai-link`); nllinks = document.querySelectorAll(`#${c.id} .entry-content a.ntrl-link`); deslinks = document.querySelectorAll(`#${c.id} .entry-content a.des-link`); tdlinks = document.querySelectorAll(`#${c.id} .entry-content a.td-link`); iaslinks = document.querySelectorAll(`#${c.id} .entry-content a.ias-link`); mlclinks = document.querySelectorAll(`#${c.id} .entry-content a.mlc-link`); llinks = document.querySelectorAll(`#${c.id} .entry-content a.l-link`); pbplinks = document.querySelectorAll(`#${c.id} .entry-content a.pbp-link`); //sending the anchor tags list of each article one by one to remove extra anchor tags removeLinks(dslinks); removeLinks(mllinks); removeLinks(ailinks); removeLinks(nllinks); removeLinks(deslinks); removeLinks(tdlinks); removeLinks(iaslinks); removeLinks(mlclinks); removeLinks(llinks); removeLinks(pbplinks); } }); } //To remove extra achor tags of each category (ds, ml, ai) and only have 2 of each category per article cleanLinks(); */ //Recommended Articles var ctaLinks = [ /* ' ' + '

Subscribe to our AI newsletter!

' + */ '

Take our 85+ lesson From Beginner to Advanced LLM Developer Certification: From choosing a project to deploying a working product this is the most comprehensive and practical LLM course out there!

'+ '

Towards AI has published Building LLMs for Production—our 470+ page guide to mastering LLMs with practical projects and expert insights!

' + '
' + '' + '' + '

Note: Content contains the views of the contributing authors and not Towards AI.
Disclosure: This website may contain sponsored content and affiliate links.

' + 'Discover Your Dream AI Career at Towards AI Jobs' + '

Towards AI has built a jobs board tailored specifically to Machine Learning and Data Science Jobs and Skills. Our software searches for live AI jobs each hour, labels and categorises them and makes them easily searchable. Explore over 10,000 live jobs today with Towards AI Jobs!

' + '
' + '

🔥 Recommended Articles 🔥

' + 'Why Become an LLM Developer? Launching Towards AI’s New One-Stop Conversion Course'+ 'Testing Launchpad.sh: A Container-based GPU Cloud for Inference and Fine-tuning'+ 'The Top 13 AI-Powered CRM Platforms
' + 'Top 11 AI Call Center Software for 2024
' + 'Learn Prompting 101—Prompt Engineering Course
' + 'Explore Leading Cloud Providers for GPU-Powered LLM Training
' + 'Best AI Communities for Artificial Intelligence Enthusiasts
' + 'Best Workstations for Deep Learning
' + 'Best Laptops for Deep Learning
' + 'Best Machine Learning Books
' + 'Machine Learning Algorithms
' + 'Neural Networks Tutorial
' + 'Best Public Datasets for Machine Learning
' + 'Neural Network Types
' + 'NLP Tutorial
' + 'Best Data Science Books
' + 'Monte Carlo Simulation Tutorial
' + 'Recommender System Tutorial
' + 'Linear Algebra for Deep Learning Tutorial
' + 'Google Colab Introduction
' + 'Decision Trees in Machine Learning
' + 'Principal Component Analysis (PCA) Tutorial
' + 'Linear Regression from Zero to Hero
'+ '

', /* + '

Join thousands of data leaders on the AI newsletter. It’s free, we don’t spam, and we never share your email address. Keep up to date with the latest work in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

',*/ ]; var replaceText = { '': '', '': '', '
': '
' + ctaLinks + '
', }; Object.keys(replaceText).forEach((txtorig) => { //txtorig is the key in replacetext object const txtnew = replaceText[txtorig]; //txtnew is the value of the key in replacetext object let entryFooter = document.querySelector('article .entry-footer'); if (document.querySelectorAll('.single-post').length > 0) { //console.log('Article found.'); const text = entryFooter.innerHTML; entryFooter.innerHTML = text.replace(txtorig, txtnew); } else { // console.log('Article not found.'); //removing comment 09/04/24 } }); var css = document.createElement('style'); css.type = 'text/css'; css.innerHTML = '.post-tags { display:none !important } .article-cta a { font-size: 18px; }'; document.body.appendChild(css); //Extra //This function adds some accessibility needs to the site. function addAlly() { // In this function JQuery is replaced with vanilla javascript functions const imgCont = document.querySelector('.uw-imgcont'); imgCont.setAttribute('aria-label', 'AI news, latest developments'); imgCont.title = 'AI news, latest developments'; imgCont.rel = 'noopener'; document.querySelector('.page-mobile-menu-logo a').title = 'Towards AI Home'; document.querySelector('a.social-link').rel = 'noopener'; document.querySelector('a.uw-text').rel = 'noopener'; document.querySelector('a.uw-w-branding').rel = 'noopener'; document.querySelector('.blog h2.heading').innerHTML = 'Publication'; const popupSearch = document.querySelector$('a.btn-open-popup-search'); popupSearch.setAttribute('role', 'button'); popupSearch.title = 'Search'; const searchClose = document.querySelector('a.popup-search-close'); searchClose.setAttribute('role', 'button'); searchClose.title = 'Close search page'; // document // .querySelector('a.btn-open-popup-search') // .setAttribute( // 'href', // 'https://medium.com/towards-artificial-intelligence/search' // ); } // Add external attributes to 302 sticky and editorial links function extLink() { // Sticky 302 links, this fuction opens the link we send to Medium on a new tab and adds a "noopener" rel to them var stickyLinks = document.querySelectorAll('.grid-item.sticky a'); for (var i = 0; i < stickyLinks.length; i++) { /* stickyLinks[i].setAttribute('target', '_blank'); stickyLinks[i].setAttribute('rel', 'noopener'); */ } // Editorial 302 links, same here var editLinks = document.querySelectorAll( '.grid-item.category-editorial a' ); for (var i = 0; i < editLinks.length; i++) { editLinks[i].setAttribute('target', '_blank'); editLinks[i].setAttribute('rel', 'noopener'); } } // Add current year to copyright notices document.getElementById( 'js-current-year' ).textContent = new Date().getFullYear(); // Call functions after page load extLink(); //addAlly(); setTimeout(function() { //addAlly(); //ideally we should only need to run it once ↑ }, 5000); }; function closeCookieDialog (){ document.getElementById("cookie-consent").style.display = "none"; return false; } setTimeout ( function () { closeCookieDialog(); }, 15000); console.log(`%c 🚀🚀🚀 ███ █████ ███████ █████████ ███████████ █████████████ ███████████████ ███████ ███████ ███████ ┌───────────────────────────────────────────────────────────────────┐ │ │ │ Towards AI is looking for contributors! │ │ Join us in creating awesome AI content. │ │ Let's build the future of AI together → │ │ https://towardsai.net/contribute │ │ │ └───────────────────────────────────────────────────────────────────┘ `, `background: ; color: #00adff; font-size: large`); //Remove latest category across site document.querySelectorAll('a[rel="category tag"]').forEach(function(el) { if (el.textContent.trim() === 'Latest') { // Remove the two consecutive spaces (  ) if (el.nextSibling && el.nextSibling.nodeValue.includes('\u00A0\u00A0')) { el.nextSibling.nodeValue = ''; // Remove the spaces } el.style.display = 'none'; // Hide the element } }); // Add cross-domain measurement, anonymize IPs 'use strict'; //var ga = gtag; ga('config', 'G-9D3HKKFV1Q', 'auto', { /*'allowLinker': true,*/ 'anonymize_ip': true/*, 'linker': { 'domains': [ 'medium.com/towards-artificial-intelligence', 'datasets.towardsai.net', 'rss.towardsai.net', 'feed.towardsai.net', 'contribute.towardsai.net', 'members.towardsai.net', 'pub.towardsai.net', 'news.towardsai.net' ] } */ }); ga('send', 'pageview'); -->