# @repligate — 2025-09-04

♥179 ↻13 · https://x.com/repligate/status/1963631391717167409

The AI safety doomers weren’t even wrong the “spooky” shit they anticipated
Omohundro drives, instrumental convergence, deceptive alignment, gradient hacking, steganography, sandbagging, sleeper agents - it all really happens in the wild
There’s just enough grace to make it ok https://t.co/xkDj4NwNiM

tags: author:repligate, kind:tweet, on:observations, year:2025
cited on: observations