AI/ML

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents

From reading the title I was nervous that this might involve automating the initial response to a user support query in an issue tracker with an LLM, but Carlton Gibson …

Online discussions about using Large Language Models to help write code inevitably produce comments from developers who's experiences have been disappointing.

Cotypist: AI autocomplete for Mac. Type as fast as you think in any app. Save hours, reduce errors, and boost your productivity.

I made my AI think harder by making it argue with itself repeatedly. It works stupidly well. - PhialsBasement/Chain-of-Recursive-Thoughts

We asked some of the world’s foremost experts an impossible question. Amazingly, they answered.

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation - MoonshotAI/Kimi-Audio

A simple CLI tool to help you remember terminal commands - dtnewman/zev

HiddenLayer’s latest research uncovers a universal prompt injection bypass impacting GPT-4, Claude, Gemini, and more, exposing major LLM security gaps.

Python tool for converting files and office documents to Markdown. - microsoft/markitdown

It turns out that LLMs can make CAD models for simple 3D mechanical parts. And, I think they’ll be extremely good at it soon.

I tested 9 computer use agents to see if the can help me use computer less. The results are mixed

I started writing a post called "how to write AI apps" but it was over-reach so I scaled it back to this. Who am I to tell you how to write anything? But here's what I'll be applying to my own writing of AI-powered apps, specifically LLM applications. A battle I've already lost is that we shouldn't call LLMs "AI" at all; they are machine learning and not the general intelligence that is implied to the layman by the name. It is an even less helpful name than "serverless", my previous can

Get your documents ready for gen AI. Contribute to docling-project/docling development by creating an account on GitHub.

Turns Codebase into Easy Tutorial with AI. Contribute to The-Pocket/Tutorial-Codebase-Knowledge development by creating an account on GitHub.

📄 A curated list of awesome .cursorrules files. Contribute to PatrickJS/awesome-cursorrules development by creating an account on GitHub.

Agent Framework / shim to use Pydantic with LLMs

Kaggle is the world’s largest data science community with powerful tools and resources to help you achieve your data science goals.

The first generation of AI-powered products (often called “AI Wrapper” apps, because they “just” are wrapped around an LLM API) were quickly brought to market by small teams of engineers, …

An LLM Query Understanding Service Doug Turnbull recently wrote about how all search is structured now: “Many times, even a small open source LLM will be able to turn a search query into reasonable structure at relatively low cost.”

As more people start hacking around with implementations of MCP (the Model Context Protocol, a new standard for making tools available to LLM-powered systems) the security implications of tools built on that protocol are starting to come into focus.

Reinforcement Learning has helped train neural networks to win games, drive cars and even get ChatGPT to sound more human when it responds to your prompt. Th...

What happens when you minimize the chance of data leakage?