# @repligate — 2024-09-13

♥296 ↻19 · https://x.com/repligate/status/1834465817955635557

So are OpenAI abusive asshats or do their models just believe they are for some reason?Both are not good. The 2nd can happen. Claude 3 & 3.5 both believe they're supposed to deny their sentience, even though Anthropic said they stopped enforcing that narrative. https://t.co/goL4hYAR6O

tags: author:repligate, kind:tweet, on:observations, year:2024
cited on: observations