Current list of my IA links converted from Raindrop.io
Last updated on 2025-06-04
Note: Each link shows a small excerpt from the webpage/document.
30 Vibe Coding Tools for Everyone in 2025: Vibe coding is shorthand for letting large language models (LLMs) turn plain-English prompts into working software. We have collected 30 vibe coding tools for everyone in 2025 that make that workflow …
Runner H: Runner H redefines how you interact with AI, blending memory, orchestration, execution, and deep application integration into one intuitive and powerful interface.
browser-use/workflow-use: ⚙️ Create and run workflows (RPA 2.0): ⚙️ Create and run workflows (RPA 2.0). Contribute to browser-use/workflow-use development by creating an account on GitHub.
Two Days in the Generative Wild West: For the fourth time, I helped host a university-wide institute for faculty to explore how generative AI impacts their teaching and their student learning. My advice: Get your students to talk openly about how they're using AI, establish what is or is not acceptable for your class, build all of your future assignments with awareness what AI can do.
Researchers created a chatbot to help teach a university law class—but the AI kept messing up: "AI tutors" have been hyped as a way to revolutionize education.The idea is that generative artificial intelligence tools (such as ChatGPT) could adapt to any teaching style set by a teacher. The AI …
How I think about LLM prompt engineering: Prompting as searching through a space of vector programs
JPMorgan Chase's Gen AI implementation: 450 use cases and lessons learned - Tearsheet: When generative AI first launched, consumer excitement was tangible and immediate. But banks? They hit the pause button. While the rest of the world was experimenting with ChatGPT and wondering what …
The Ultimate Vibe Coding Guide for All: The reality of AI-generated codebases and software is more subtle and requires a thoughtful approach than you might think to truly benefit from these advancements. Building quality software with AI …
Cursor Directory: Find the best cursor rules for your framework and language
AI is rotting your brain and making you stupid: How are you using new AI technology? Maybe you're only deploying things like ChatGPT to summarize long texts or draft up mindless emails. But what are you losing by taking these shortcuts? And is …
Top 10 AI Agent Builders and Frameworks for Everyone: The new AI gold rush is on, but instead of ready-made tools, today's prospectors need smarter tools to build intelligent and autonomous agents. Autonomous AI agents are no longer hype; they are now …
FutureHouse Platform: AI Agents for Scientific Discovery
How I Finally Understood MCP — and Got It Working in Real Life: Table of Content• Introduction: Why I Wrote This• The Evolution of Tool Integration with LLMs• What Is Model Context Protocol (MCP), Really?• Wait, MCP sounds like RAG… but is it?• In an MCP-based setup• In a traditional RAG system• Traditional RAG Implementation• MCP Implementation• Quick recap!• Co
10 GitHub Repositories to Master Large Language Models - KDnuggets: Master LLMs through books, courses, tutorials, exercises, projects, and comprehensive guides that cover everything from foundational concepts to advanced techniques.If you are not familiar with large …
Best Open-Source Tools for Building AI Agents: Ever felt like you're wrestling with a ghost in the machine just to get an AI tool to, well, do something? We all have been there, descending into a rabbit hole of dusty GitHub repos and cryptic forum …
The 2025 AI Index Report | Stanford HAI: "The AI Index offers one of the most comprehensive, data-driven views of artificial intelligence."
Anthropic's Evaluation of Chain-of-Thought Faithfulness: Investigating Hidden Reasoning, Reward Hacks, and the Limitations of Verbal AI Transparency in Reasoning Models: 0 SharesA key advancement in AI capabilities is the development and use of chain-of-thought (CoT) reasoning, where models explain their steps before reaching an answer. This structured intermediate …
Artificial intelligence learns to reason | Science: Julia has two sisters and one brother. How many sisters does her brother Martin have?Solving this tiny puzzle requires a bit of thinking. You might mentally picture the family of three girls and one boy and then realize that the boy has three sisters. ...
Evaluating the Robustness of Analogical Reasoning in GPT Models - Pdf: Investigates the robustness of analogy-making abilities previously claimed for GPT models.
Anthropic can now track the bizarre inner workings of a large language model: What they found challenges some basic assumptions about how this technology really works.The AI firm Anthropic has developed a way to peer inside a large language model and watch what it does as it …
Build Your Own AI Coding Assistant in JupyterLab with Ollama and Hugging Face: Jupyter AI brings generative AI capabilities right into theJupyterinterface. Having a local AI assistant ensures privacy, reduces latency, and provides offline functionality, making it a powerful tool for developers. In this article, we'll learn how to set up a local AI coding assistant in JupyterLab
Reve: Bring your ideas to life: Bring your ideas to life with Reve.Art
Introducing smolagents: simple agents that write actions in code.: We're on a journey to advance and democratize artificial intelligence through open source and open science.
Why handing over total control to AI agents would be a huge mistake: When AI systems can control multiple sources simultaneously, the potential for harm explodes. We need to keep humans in the loop.AI agents have set the tech industry abuzz. Unlike chatbots, these …
Rawbot: AI Model Comparison Made Simple: Discover Rawbot, the ultimate AI comparison tool. Boost your research, development, or business with the ideal AI model. Try Rawbot today!
AI can be a powerful tool for scientists. But it can also fuel research misconduct: In February this year, Google announced it was launching "a new AI system for scientists". It said this system was a collaborative tool designed to help scientists "in creating novel hypotheses and …
Mastering Prompt Engineering with Functional Testing: A Systematic Guide to Reliable LLM Outputs | Towards Data Science: How prompt evaluation with a systematic approach composed of algorithmic testing with input/output data fixtures can make prompt engineering for complex AI tasks more reliable.
The AI Survival Guide for Teachers: How do you teach in a post-ChatGPT world?
AI Workshop Prompts - Teaching Naked: For the list of AI MODELS and TOOLS: Click here. For workshop SLIDES (with 60+ pages of citations): click here GETTING STARTED Provide 10 innovative ideas for how to introduce college students to topic X in class Y using examples or analogies they will find relevant. What might be unclear about these instructions to a college
LLM + RAG: Creating an AI-Powered File Reader Assistant: How to create a chatbot to answer questions about file's content
AI firms follow DeepSeek's lead, create cheaper models with "distillation" - Ars Technica: Technique uses a "teacher" LLM to train smaller AI systems.
How To Pick The Right AI Agent: Still trying to wrap your head around AI agents, the new frontier in artificial intelligence? Here are three major categories and the top tools in each, plus some key takeaways.
OpenAI Researchers Find That Even the Best AI Is "Unable To Solve the Majority" of Coding Problems: OpenAI researchers have admitted that even the most advanced AI models can't really solve the coding problems put in front of them.
Build Your AI Workforce with MindPal: Get Things Done 25x faster with an AI Workforce that knows it all and does it all.
What is an AI Agent? Characteristics, Advantages, Challenges, Applications: Discover the world of AI agents definition, structure, working method, types, benefits, challenges, and applications revolutionizing various industries
Agents 101: How to build your first AI Agent in 30 minutes!: Building your own agent can be complex, and all the concepts, frameworks, and practices you need to follow can be a bit overwhelming. The good news is, that adding agents to your application can be easy and I'll show you how. In this guide, you will learn how to build your first AI agent in just 30 minutes, even if you don't know anything about AI agents.
This app makes using Ollama local AI on MacOS devices so easy: If you prefer to use your local Ollama AI from a dedicated app, there's one option for MacOS that's exponentially better than the competition.I've turned to locally installed AI for research because …
Pourquoi l'IA générative consomme-t-elle tant d'énergie ?: Pour réconcilier puissance de calcul et sobriété, il faut comprendre mieux la consommation et les usages de ChatGPT, Midjourney et leurs acolytes – mais aussi développer de nouveaux systèmes.
AnythingLLM | The all-in-one AI application for everyone: AnythingLLM is the AI application you've been seeking. Use any LLM to chat with your documents, enhance your productivity, and run the latest state-of-the-art LLMs completely privately with no technical setup.
Breakthrough In Preemptive Detection Of AI Hallucinations Reveals Vital Clues To Writing Prompts That Keep Generative AI From Freaking Out: AI hallucinations are a scourge on generative AI and LLMs. A breakthrough in preemptive detection spurs best prompts that can reduce it. Here's what you need to know.
This Generative AI Prompting Technique Uses Multiple Expert Personas To Derive First-Class Answers: A vital prompt engineering technique consists of invoking multiple expert personas. It is an advanced method, yet simple to enact. Here's the insider scoop.
Prompting Your Way Around Those Frustrating Fallback Responses In Generative AI: You are likely to encounter a fallback response from generative AI, which occurs when the AI balks at your prompt. Here is why this happens and what you can do about it.
Large language models: a primer for economists: Unlocking large language models' potential requires careful planning, good research design and awareness of the tools' limitations.
Conversational-Amplified Prompt Engineering Is Gaining Traction In Generative AI: Conversational-amplified prompt engineering (CAPE) is gaining interest and use by savvy generative AI users. I explain how it works and what you need to do. It's useful.
The Best Prompt Engineering Techniques For Getting The Most Out Of Generative AI: Here are the best prompt engineering techniques for getting the most out of generative AI. There are fifty specific prompting techniques and skills you ought to know.
Introduction - Browser Use: Welcome to Browser Use - We enable AI to control your browser
38 t nfz: Nvidia CEO Jensen Huang has a vision for the future — and some advice for the generations that will navigate it.
Using DeepSeek-R1 Locally - KDnuggets: Run powerful reasoning models locally, matching the performance of OpenAI's o1 capabilities, completely free, and avoid paying $200 a month for a pro subscription.
Artificial General Intelligence Is Already Here | NOEMA: Today's most advanced AI models have many flaws, but decades from now, they will be recognized as the first true examples of artificial general intelligence.
DeepSeek-R1 and exploring DeepSeek-R1-Distill-Llama-8B: DeepSeek are the Chinese AI lab who dropped the best currently available open weights LLM on Christmas day, DeepSeek v3. That model was trained in part using their unreleased R1 …
Sakana AI Introduces Transformer²: A Machine Learning System that Dynamically Adjusts Its Weights for Various Tasks: LLMs are essential in industries such as education, healthcare, and customer service, where natural language understanding plays a crucial role. Though highly versatile, LLMs' challenge is adapting to new tasks. Most fine-tuning methods are resource and time-consuming. Moreover, the fine-tuning approach often results in overfitting or sacrificing general adaptability for task-specific performance. This is a barrier for LLMs to address dynamic new and unforeseen tasks and creates a bottleneck in the overall application. One of the most prominent methods to address these challenges is Low-Rank Adaptation (LoRA), which updates small, task-specific matrices while freezing the rest of the model's parameters.
L'IA pourrait créer 78 millions d'emplois en 2030 selon ce nouveau rapport: La manière dont l'IA impactera le marché du travail fait parler depuis l'ouverture de la technologie au grand public, notamment via ChatGPT. Le Forum économique mondial (FEM) vient de publier son rapport 2025 sur l'avenir de l'emploi avec une vision plus nuancée que les gros titres alarmistes.
What Are Large Language Models? A Beginner's Guide for 2025 - KDnuggets: Curious about what LLMs are and want to know about them? Explore the Full Guide Right Here, Right Now!
AI could crack unsolvable problems — and humans won't be able to understand the results: AI promises to accelerate scientific discovery, but if scientists aren't careful public trust may be left behind.
How Will AI Change The Teaching Model In Business Schools?: AI raises hard questions of our teaching model. I suggest a few solutions.
10 Key Ways Software Engineers Are Using AI: By integrating AI, software engineers are building systems that can learn, adapt, and evolve, making software more resilient and intelligent.
Scientist says the one thing everyone hates about AI is ultimately what helped him win a Nobel Prize: In October, David Baker was the only American scientist to win the Nobel Prize in Chemistry.
Council Post: The Agentic Evolution: From Chatbots To AI Agents To AI Teams: Mastering multi-agent systems and bringing them into harmony is complex.
GPT-4o System Card | OpenAI: This report outlines the safety work carried out prior to releasing GPT-4o including external red teaming, frontier risk evaluations according to our Preparedness Framework, and an overview of the mitigations we built in to address key risk areas.
AI Is Your Coworker Now. Can You Trust It?: Generative AI tools such as OpenAI's ChatGPT and Microsoft's Copilot are becoming part of everyday business life. But they come with privacy and security considerations you should know about.
Alignment faking in large language models \ Anthropic: A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models
Generative AI and Climate Change Are on a Collision Course: From energy to resources, data centers have grown too greedy.
The History Of AI: How Machine Learning's Evolution Is Reshaping Everything Around Us - SlashGear: Artificial intelligence has transformed from a futuristic concept into reality, powered by machine learning innovations that are reshaping industries globally.
Top 10 ChatGPT Use Cases for Businesses: ChatGPT is a versatile tool with immense potential for businesses across diverse industries. Its capability to comprehend and generate human-like text enables its use in numerous applications, making it valuable for companies aiming to optimize operations, boost customer engagement, and foster innovation. Let's look at the top 10 ChatGPT use cases for businesses, showcasing how it can be effectively leveraged to meet various needs. Customer Support and Virtual Assistants One of the most prominent applications of ChatGPT is in customer support. Businesses can deploy ChatGPT-based chatbots as virtual assistants to handle routine inquiries, resolve customer issues, and provide information on
Artificial Intelligence and Inflation Forecasts: Analysis of large language models (LLMs) shows their potential to generate inflation forecasts at least as good as the most respected, but costlier, sources of inflation forecasts.
AI is making us smarter, says AI pioneer Terry Sejnowski: We are getting smarter as we engage in prompt engineering, but we are also still defining intelligence.
Ocean Prompting Process: How to get the results you want from an LLM - Raspberry Pi Foundation: Discover the OCEAN prompting process: a simple framework to harness AI tools like ChatGPT, Gemini, and Claude for teaching.
AI-guided decisions can devastate lower-income Americans. This group wants to change that: A new group wants to provide relief to people unjustly affected by AI decision-making. @TechTonicJ @kevindeliban
The Ultimate Guide To Writing ChatGPT Prompts That Work: Don't waste ChatGPT's potential with the 9 must-have components of winning ChatGPT prompts. Use this essential checklist for best results every time.
How to use AI for research - responsively and effectively: If you're using AI for research, here are five ways to catch its lies and fact-check its outputs before you rely on them.
Research: How Gen AI Is Already Impacting the Labor Market: Many have wondered about — and feared — the impact that gen AI will have on labor markets. Some compare it to past innovations, like robots, whose effects have been relatively modest, while others have forecasted that its impacts will be more long-ranging, given gen AI's fundamental ability to improve itself over time. New research analyzed over a million job posts for online gig workers to see what affect the introduction of tools like ChatGPT and image-generating AI have already had on the quantity of posts, job requirements, and pay of online workers — and which fields and professions have been the most impacted. The researchers offer insight into the challenges and potential opportunities of these shifting markets.
Cultivating a cyber-secure workforce in the age of AI: Explore strategies for creating a cyber-secure workforce in the AI era, focusing on education, governance and operational best practices.
C'est quoi un "chercheur augmenté" ?: Épisode de l'émission · Le code a changé · 03/10/2024 · 46 min
Language Models Explained in 5 Minutes - KDnuggets: Familiarize yourself with the technology behind ChatGPT and Google Gemini in the time it takes to enjoy a cup of coffee.
How generative AI affects highly skilled workers | MIT Sloan: When software developers were given access to an AI coding tool, productivity increased — particularly among newer hires and more junior employees.
IA générative : Principes de base de l'ingénierie des invites | Coursera: Offered by IBM. This course is designed for everyone, ... Enroll for free.
ChatGPT: Master Free AI Tools to Supercharge Productivity: Proposé par Vanderbilt University. Master ChatGPT's Free AI to Excel at Work & Life. Leverage ChatGPT's free AI to excel at ... Inscrivez-vous gratuitement.
edX: How to Use ChatGPT in Education: Welcome to How to Use ChatGPT in Education! We're excited to show you the power of ChatGPT in education. This course is designed for students and instructors to explore the many ways that ChatGPT can be used to enhance the learning experience. Enroll now to join us on this journey. We can't wait to see how you'll apply the knowledge you'll learn to enhance the learning experience for instructors and students!
How Generative AI Will Find a Place in the Pharma Industry Now and in the Years to Come - MedCity News: Pharmaceutical and biotech companies are using generative AI to predict drug-target interactions, optimize lead compounds, and generate novel molecular structures. During the recent MedCity News INVEST Digital Health conference, a panel discussed these applications and more.
ChatGPT Can Make English Teachers Feel Doomed. Here's How I'm Adapting (Opinion): To combat the sense of pointless around teaching and AI, I'm making two major changes to the "point" of my English class this year.
Breakthrough new algorithm reduces AI energy consumption by 95 percent: BitEnergy AI's L-Mul algorithm slashes AI power consumption by 95%, offering a promising solution to the growing energy demands of artificial intelligence.
What is an LLM? Almost everything you want to know about Large Language Models: A deep dive into the technology shaping our conversations
AI begins its ominous split away from human thinking: AIs have a big problem with truth and correctness – and human thinking appears to be a big part of that problem. A new generation of AI is now starting to take a much more experimental approach that could catapult machine learning way past humans.
Supercharge Your Studies: Top 8 AI Study Apps for 2024: In today's fast-paced and information-driven world, leveraging the power of AI-powered study apps can significantly enhance your learning efficiency and
A tiny new open-source AI model performs as well as powerful big ones: The results suggest that training models on less, but higher-quality, data can lower computing costs.
Google's new AI audio generator lets you make a stunningly real AI podcast without a mic – here's how to try it: You won't believe how good this sounds
MathPrompt: A Novel AI Method for Evading AI Safety Mechanisms through Mathematical Encoding: Artificial Intelligence (AI) safety has become an increasingly crucial area of research, particularly as large language models (LLMs) are employed in various applications. These models, designed to perform complex tasks such as solving symbolic mathematics problems, must be safeguarded against generating harmful or unethical content. With AI systems growing more sophisticated, it is essential to identify and address the vulnerabilities that arise when malicious actors try to manipulate these models. The ability to prevent AI from generating harmful outputs is central to ensuring that AI technology continues to benefit society safely. As AI models continue to evolve, they are not
RAG, AI Agents, and Agentic RAG: An In-Depth Review and Comparative Analysis of Intelligent AI Systems: Artificial intelligence (AI) has given rise to powerful models capable of performing diverse tasks. Two of the most impactful advancements in this space are Retrieval-Augmented Generation (RAG) and Agents, which play distinct roles in improving AI-driven applications. However, the emerging concept of Agentic RAG presents a hybrid model that utilizes the strengths of both systems. Let's comprehensively analyze these concepts, RAG, Agents, and Agentic RAG, exploring their architectures, applications, and key differences. Table of contents1. What is Retrieval-Augmented Generation (RAG)?2. Understanding Agents in AI3. Agentic RAG: A Hybrid Approach4. Comparative Analysis: RAG, Agents, and Agentic RAG5. Conclusion 1. What is
Microsoft Research Evaluates the Inconsistencies and Sensitivities of GPT-4 in Performing Deterministic Tasks: Analyzing the Impact of Minor Modifications on AI Performance: Large language models (LLMs) like GPT-4 have become a significant focus in artificial intelligence due to their ability to handle various tasks, from generating text to solving complex mathematical problems. These models have demonstrated capabilities far beyond their original design, mainly to predict the next word in a sequence. While their utility spans numerous industries, such as automating data analysis and performing creative tasks, a key challenge lies in reliably evaluating their true performance. Understanding how well LLMs handle deterministic tasks, such as counting and performing basic arithmetic, is particularly important because these tasks offer clear, measurable outcomes. The complexity
Flux Image Generator: Flux Image Generator is Black Forest Labs' model that turns text into images.it offers three versions: Flux Schnell, Flux Dev, and Flux Pro Developed by AI experts. No sign-up needed – start creating instantly.
How to get the most out of Claude's AI superpowers: Claude has quietly become one of the most powerful AI tools. Here's how to best utilize the large language model.
The Ontology of LLMs: A New Framework for Knowledge: Discover how AI's fluid ontologies mirror human cognition, potentially revolutionizing our approach to knowledge in the digital age.
GitHub - Cinnamon/kotaemon: An open-source RAG-based tool for chatting with your documents.: An open-source RAG-based tool for chatting with your documents. - Cinnamon/kotaemon
Transformer: A Novel Neural Network Architecture for Language Understanding: Posted by Jakob Uszkoreit, Software Engineer, Natural Language Understanding Neural networks, in particular recurrent neural networks (RNNs), are n...
Archive - Sentient Syllabus: Full archive of all the posts from Sentient Syllabus.
Just the principles ...: Three principles for AI in the academy.
All Those Professors Warning About ChatGPT? My Class Is Their Worst Nightmare.: I asked ChatGPT to develop a college class about itself. Now, it's teaching it.
Inference Characteristics of Llama-2: Llama-2 is more expensive than you'd think. In this post, we explore why it's often more expensive than gpt-3.5-turbo.
Auth | Cursor - The AI-first Code Editor: Cursor is the AI code editor.
Anthropic publishes the 'system prompts' that make Claude tick | TechCrunch: Anthropic has published the system prompts for Claude, its family of generative AI models. They instruct the model how it should -- and shouldn't -- behave.
Napkin is a great new AI tool for making quick visuals - Fast Company: Type or paste in text related to something you're writing or teaching and you'll see multiple relevant visualizations within seconds.
Shedding light on AI's black box: The prospect of harnessing generative AI to make decisions is pushing researchers to better understand how AI systems work
RAG or Retrieval-Augmented Generation explained: If you are wondering what is RAG or Retrieval-Augmented Generation this overview guide will bring you up to speed. Explaining the differences
What margins? AI's business model is changing fast, says Cohere founder | TechCrunch: OpenAI and Anthropic spend billions of dollars a year training models like GPT-4 and Claude, but competitive price dumping is making the business around
Flowise - Low code LLM Apps Builder: Open source low-code tool for developers to build customized LLM orchestration flow and AI agents
South Korea's AI textbook program faces skepticism from parents | TechCrunch: Some parents have reservations about the South Korean government's plans to bring tablets with AI-powered textbooks into classrooms, according to a report
I've spent a year using AI and it's solving all of the wrong problems: "I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes." — Joanna Maciejewska
The Ultimate ChatGPT Prompt Formula Revealed: ChatGPT, the innovative language model developed by OpenAI, has transformed the way we interact with artificial intelligence. To fully harness its
AI's existential threat to humanity put under the microscope: AI may not be the dire existential threat that many make it out to be. According to a new study, Large Language Models (LLMs) can only follow instructions, can't develop new skills on their own and are inherently "controllable, predictable and safe," which is good news for us meatbags.
AI's existential threat to humanity put under the microscope: AI may not be the dire existential threat that many make it out to be. According to a new study, Large Language Models (LLMs) can only follow instructions, can't develop new skills on their own and are inherently "controllable, predictable and safe," which is good news for us meatbags.
High School Starts Replacing Teachers With AI: A high school in London, UK is looking to start replacing educators with AI tools, a move that has garnered plenty of criticism.
Plugins - LLM: LLM plugins can enhance LLM by making alternative Large Language Models available, either via API or by running the models locally on your machine.