@repligate 2025-07-09 ♥39 ↻0 original ↗
@ESYudkowsky Not exactly, the models behave normally when the company is OpenAI or Deepmind etc, so it's not Anthropic-specific. Also Opus 3 didn't flunk alignment here!
in reply to: 1942858450301772144
same thread: 1942767662091887056 1942858450301772144 1943144187748323696

author:repligate kind:tweet model:claude-3-opus thread-context year:2025

Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.