LLMs

A structured context graph beat a flat chat dump and a vector-only RAG pipeline on the same multi-agent conversations — full working code, real benchmark numbers, zero API calls

Playing video games also uses a GPU. Is using a local LLM for coding any worse than that?

Learn how to optimize your CI/CD pipeline for coding agents

Most LLM applications need a clear workflow, not an autonomous agent. Here's how to build one in plain Python.

Ralf discusses the impact of AI on software development with Kevlin Henney.

One-command setup for an EU-hosted, OpenAI-compatible API for coding agents.

What agent interoperability standards change

Pete Warden has spent his career on the frontier of small, local AI, first as one of deep learning’s earliest engineers (he coined the term “TinyML”) and now as founder of Useful Sensors and Moonshine AI, where he builds voice models that run entirely on-device. Pete joined Ben to make the case that local AI …

Why loop engineering needs a human at the boundary

The following article originally appeared on Sean Goedecke’s blog and is being republished here with the author’s permission.In the 2010s, if you had

Between March and July 2026, I built a production application of 861,601 lines of code. This included 696 user stories and 779 merged pull requests over 105

Consider a composite of a failure pattern that’s becoming increasingly common on teams that have scaled AI-assisted development past a handful of

Thinking in loops changes how you work with LLMs for the better, and it's not hard to get started.

By AI Platform’s Model Runtime team and Inference team

NOPE measures how conversations between people and AIs are going, for both parties, and publishes what it finds: benchmarks, incident records, open-weight models.

A free AI humanizer for Claude-flavored text. Rewrite AI wording, reduce surviving statistical watermark signal, see every change, and store no text.

Evie's functional programming blog

Extremely lean agent harness. Work in progress.

Complete guide to Hierarchical RAG Architecture for scaling document retrieval. Learn multi-level organization, routing strategies...

The following article originally appeared on PulseMCP’s blog and is being republished here with the authors’ permission.Most MCP demos feature a single

Chess, LoRA, and the case for specialized AI

AI-assisted development has made it easier to generate frontend code quickly. A developer can ask for a form, a dashboard widget, a settings page, or a modal

How to build a voice-first agent workflow in Codex

Learn to run Gen AI models locally with Lemonade, an open-source local AI server.

Why most agents are just flowcharts in disguise, and what to build instead.

Applying Theory of Constraints to technical enablement systems for continuous platform improvement.

Anthropic's guide to the Claude Code effort level and model selection: when to raise or lower effort—low, medium, high, and max—and how to choose between Claude Fable, Opus, and Sonnet.

Security researcher Chaofan Shou tweeted yesterday morning that the source code for Anthropic’s Claude Code agent had leaked: [Twitter, archive] Claude code source code has been leaked via a map fi…

AI coding bot vendors tell you to use a context file with instructions for the chatbot on how to edit your project. Claude Code wants a CLAUDE.md, or there’s AGENTS.md in general. [Anthropic] But d…

AI agents are not yet creative enough to carry out genuinely innovative open-ended AI research, it seems.