🏠 Welcome | Boundary Documentation
BAML is a domain-specific language to generate structured outputs from LLMs — with the best developer experience.
Teaching LLMs how to solid model
PicoLM
A Lightweight Framework for Studying Learning Dynamics Pico demystifies how language models learn. Lightweight and efficient, it's your go-to toolkit for…
Agents
Chip Huyen's 8,000 word practical guide to building useful LLM-driven workflows that take advantage of tools. This article is adapted from "AI Engineering"…
A Simple Guide to Retrieval Augmented Generation
Book outline: The components of a RAG system How to create a RAG knowledge base The indexing and generation pipeline Evaluating a RAG system Advanced RAG…
johnbean393/Sidekick: A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software. Powered by llama.cpp.
A native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing…
Reinforcement Learning: An Introduction : Andrew Barto and Richard S. Sutton : Internet Archive
Textbook, second edition
DuckDB goes distributed? DeepSeek’s smallpond takes on Big Data
DeepSeek is pushing DuckDB beyond its single-node roots with smallpond, a new, simple approach to distributed compute. But does it solve the scalability…
Lil'Log
good blog on LLM, Machine Learning etc
Minions: the rise of small, on-device LMs
shift a substantial portion of LLM workloads to consumer devices by having small on-device models collaborate with frontier models in the cloud. By only…
deepseek-ai/awesome-deepseek-integration
consistent with an opensource mindset, deepseek are curating a list of "awesome" stuff built with/on deepseek. This list not only serves as a reminder of what…
Windsurf Editor by Codeium
I have some suggest windsurf as an alternative for Cursor, just days after I paid for annual subscription.. sigh.. In either case, there is nothing stopping me…
Claude 3.7 Sonnet and Claude Code Anthropic
Anthropic announced new version of Claude today, and it has been received very positively going by the reactions on X. Simon Willison ran it through his usual…
Sky-T1: Train your own O1 preview model within $450
Stanford's Sky Lab announced the "Sky-T1" model that performs competitively in reasoning and coding while comparison to OpenAI's o1 model, while using a small…
Aurora - foundation model of the atmosphere from Microsoft
Came across this model today at Work. Needs an A100 for inference. Paper is here: [[2405.13063] A Foundation Model for the Earth…
[2501.09223] Foundations of Large Language Models
Tune Llama3 405B on AMD MI300x (our journey) - Felafax Blog - Obsidian Publish
8 Google Employees Invented Modern AI. Here’s the Inside Story | WIRED
a profile of the people that co-authored "Attention is all you need" paper that was the turning point in the evolution of LLMs.
Let's Build AI
A community-driven platform for AI enthusiasts.
[2403.09611] MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
From Apple In this work, we discuss building performant Multimodal Large Language Models (MLLMs). In particular, we study the importance of various…
[2403.09629] Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
When writing and talking, people sometimes pause to think. Although reasoning-focused works have often framed reasoning as a method of answering questions or…
stanfordnlp/dspy: DSPy: The framework for programming—not prompting—foundation models
DSPy is a framework for algorithmically optimizing LM prompts and weights, especially when LMs are used one or more times within a pipeline. To use LMs to…
mufeedvh/code2prompt: A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.
You can run this tool on the entire directory and it would generate a well-formatted Markdown prompt detailing the source tree structure, and all the code. You…
Cognition Labs Blog - developers of Devin AI assistant
Introducing Devin, the first AI software engineer And setting a new state of the art on the SWE-bench coding benchmark Meet Devin, the world’s first fully…
Introducing gigaGPT: GPT-3 sized models in 565 lines of code - Cerebras
ChatGPT Explained: A Normie's Guide To How It Works