Stay informed with the latest trends, tutorials, and breakthroughs in artificial intelligence from the DAIR.AI team.
June 21, 2026
Most note systems rot because nothing maintains them. Over 30 short terminal lessons, turn one messy vault into a knowledge operations system you actually use, by driving a real agent yourself.
June 21, 2026
You do not need API keys or code to generate images with AI. Use a prebuilt agent skill to create, iterate on, and edit images, and learn the prompt design habits that make the difference.
June 21, 2026
What is the big deal with loop engineering and autonomous long-running agents? A look at how goals, evaluators, loops, and artifacts let coding agents keep working after the human stops typing.
June 21, 2026
Agent Skills turn a general-purpose AI agent into a specialist for the work you actually do. Here is how to build and test your first reusable Skill in under an hour, step by step in a live sandbox.
June 21, 2026
A good tutor adapts to you. The /teach skill turns Hermes Agent into an interactive tutor that builds a structured curriculum on any topic you want, then teaches it lesson by lesson.
June 21, 2026
Keyword checks cannot grade a freeform answer. Learn to build an LLM judge from scratch, validate it against human labels, and harden it against bias so you can trust your evaluations.
June 21, 2026
Reading about prompt engineering does not make you good at it. Build the skill the only way that sticks, by writing real prompts and watching what changes, from a single sentence to a fully engineered prompt.
May 1, 2026
Wiki Builder is an open-source Claude Code plugin that turns the LLM-knowledge-base workflow into a one-command setup. Scaffold a configurable wiki, point Claude at sources, and let the agent compile durable pages, indexes, and concept maps for you.
April 27, 2026
A hands-on guide to building a simple LLM knowledge base with raw markdown sources, a compiled wiki, reusable prompts, and an agent that keeps improving the knowledge base over time.
April 3, 2026
A visual breakdown of Andrej Karpathy's approach to building personal knowledge bases powered by LLMs. Learn the 4-phase pipeline: ingest, compile, query, and maintain - with an interactive architecture diagram.
February 26, 2026
We tested Google's new Nano Banana 2 image generation model (gemini-3.1-flash-image-preview) against Nano Banana Pro across six experiments. Here's what improved in text rendering, object fidelity, search grounding, and what it means for your image generation workflows.
February 25, 2026
ETH Zurich evaluates whether AGENTS.md and CLAUDE.md context files actually improve coding agent performance. Human-written files help (+4%), LLM-generated files hurt (-2%), and all files add 20%+ cost. Introduces the AGENTbench benchmark.
February 17, 2026
LCM introduces deterministic context management for LLM agents, replacing model-written recursion with engine-controlled primitives. Its coding agent, Volt, outperforms Claude Code on the OOLONG long-context benchmark. Here's how it works and why it matters.
February 16, 2026
The next big thing might be recursive language models (RLMs). Instead of cramming text into the context window, RLMs treat text as an external environment that the model programs against. Here's why an 8B model can rival GPT-5 on long-context tasks.
February 3, 2026
A hands-on tutorial on using the image generator plugin in Claude Code. Learn how to generate images from text prompts, edit existing photos, create blog covers, product mockups, logos, and more - all from your terminal.
February 1, 2026
We're excited to launch DAIR.AI Academy, a new learning platform designed to help you master AI through expert-led courses, hands-on projects, and a vibrant community of builders.