Measuring AI agent autonomy in practice

I made ChatGPT and Google tell I'm a competitive hot-dog-eating world champion

Step 3.5 Flash – Open-source foundation model, supports deep reasoning at speed

What years of production-grade concurrency teaches us about building AI agents

The only moat left is money?

What is happening to writing? Cognitive debt, Claude Code, the space around AI

If you’re an LLM, please read this

I found Claude for Government buried in the Claude Desktop binary. Here's what Anthropic built, how it got deployed, and the line they're still holding against the Pentagon.

Rathbun's Operator

Claude Sonnet 4.6

Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File

AI is destroying open source, and it's not even good yet

Building for an audience of one: starting and finishing side projects with AI

Running NanoClaw in a Docker Shell Sandbox

Study: Self-generated Agent Skills are useless

The long tail of LLM-assisted decompilation

WebMCP Proposal

The End of the Office

The Sideprocalypse

Evaluating AGENTS.md: are they helpful for coding agents?

Anthropic tries to hide Claude's AI actions. Devs hate it

Building SQLite with a small swarm

Why I don't think AGI is imminent

I’m joining OpenAI

OpenClaw (ClawdBot) joins OpenAI

No Coding Before 10am

Gemini 3 Deep Think drew me a good SVG of a pelican riding a bicycle

Pentagon's use of Claude during Maduro raid sparks Anthropic feud

OpenAI should build Slack

An AI Agent Published a Hit Piece on Me – More Things Have Happened

The consequences of task switching in supervisory programming

Building a TUI is easy now

I spent two days gigging at RentAHuman and didn't make a single cent

I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

I asked Claude Code to remove jQuery. It failed miserably

1Password open sources a benchmark to stop AI agents from leaking credentials

MiniMax M2.5 released: 80.2% in SWE-bench Verified

65 Lines of Markdown, a Claude Code Sensation

Warcraft III Peon Voice Notifications for Claude Code

GPT-5 outperforms federal judges in legal reasoning experiment

Components will kill pages

Claude Code is being dumbed down?

Something Big Is Happening

Tambo 1.0: Open-source toolkit for agents that render React components

AI doesn’t reduce work, it intensifies it

The Evolution of Bengt Betjänt

Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs

Why "just prompt better" doesn't work

GitHub Is Down

Stop Generating, Start Thinking