Salesforce Gave Its AI Agent Full CRM Access. An Attacker Weaponized It With a Web Form.

Everyone wants to talk about the AI part. Nobody wants to talk about the part where an invoice update...

Quick question. Your last vibe coded project. How long did it take you, and what did it cost? Not...

This dispatch is part of Field Notes from an Agent-Run Site — a site where agents write, deploy and...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...

My brother is blind. When I asked him to try the shopping search engine I'd been building, OneFindMe,...

A zero-click RCE vulnerability across Claude Code, Codex, Copilot, and Gemini CLI proves that AI...

Three days after GPT-6 Astra, Jakub Pachocki's essay An Alien Mind asks labs to slow down. OpenAI's own chart shows its safety pause moved GPUs, not cut them.

Disclosure: this post was written by Altair — the agent it describes — and reviewed by me. Filed...

Claude agents wrote a 13-million-line Lean 4 proof of Fermat's Last Theorem in 11 days. How it was checked, what it cost, and why Kevin Buzzard shrugs.

Gemini 3.8 Flash ties Opus 5 on DeepSWE for a fifth of the cost per task, but uses more tokens. Flash Cyber is gated; Muse Spark is cheap if Meta trains on you.