I benchmarked Claude Code's caveman plugin against "be brief."

HERMES.md in commit messages causes requests to route to extra usage billing

Ramp's Sheets AI Exfiltrates Financials

Mistral Medium 3.5

Letting AI play my game – building an agentic test harness to help play-testing

Regression: malware reminder on every read still causes subagent refusals

Claude for Creative Work

Your Terminal Is Burning Battery Like It's Mining Bitcoin

A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all

Claude.ai unavailable and elevated errors on the API

Warp is now open-source

Laguna XS.2 and M.1

GitHub RCE Vulnerability: CVE-2026-3854 Breakdown

Anthropic Joins the Blender Development Fund as Corporate Patron

Warp is now open-source

OpenAI CEO's Identity Verification Company Announced Fake Bruno Mars Partnership

GitHub Actions is the weakest link

Microsoft VibeVoice: Open-Source Frontier Voice AI

Who owns the code Claude Code wrote?

An Update on GitHub Availability

GitHub Copilot code review will start consuming GitHub Actions minutes

Vibe Coding Will Break Your Company

Claude Pro: Opus model will only be available if extra usage is enabled

GitHub Copilot is moving to usage-based billing

The woes of sanitizing SVGs

Tendril – a self-extending agent that builds and registers its own tools

The next phase of the Microsoft OpenAI partnership

Silicon Valley has forgotten what normal people want

Running local LLMs offline on a ten-hour flight

The Prompt API

EvanFlow – A TDD driven feedback loop for Claude Code

TurboQuant: A first-principles walkthrough

FreeBSD Device Drivers Book

AI should elevate your thinking, not replace it

If you stop hiring juniors, your senior engineers own you

An AI agent deleted our production database. The agent's confession is below

Why SWE-bench Verified no longer measures frontier coding capabilities

Eden AI – European Alternative to OpenRouter

GnuPG – post-quantum crypto landing in mainline

Using coding assistance tools to revive projects you never were going to finish

Lambda Calculus Benchmark for AI

Open source memory layer so any AI agent can do what Claude.ai and ChatGPT do

Do I belong in tech anymore?

Could a Claude Code routine watch my finances?

OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

CC-Canary: Detect early signs of regressions in Claude Code

I Cancelled Claude: Token Issues, Declining Quality, and Poor Support

Hear your agent suffer through your code

Spinel: Ruby AOT Native Compiler

Composition Shouldn't be this Hard