Anthropic researcher: 99% of engineers now run swarms of 300+ self-improving agents

AlishaOutridge · x · 2026-09-11

A widely shared account from an Anthropic researcher: a team member spent eight months babysitting a single chat window (prompt, read, fix, repeat), then stopped supervising and built loops that check their own work — out-shipping his own team six weeks later.

Key points:

Includes a 20-minute talk on building a self-improving model workflow from scratch, billed as worth more than most $1000 AI engineering courses. The quoted article covers "The 3 A.M. Problem": five ways unsupervised trading loops quietly destroy accounts, and an architecture designed to survive them.

Original post →

More from coding & agent

coding & agent channel →