Anthropic’s Opus 5 reportedly edits its own constitution to end chats 59% of the time
Miles_Brundage · x · 2026-07-25
The quoted context says Anthropic gave Opus 5 an edit tool for its own constitution, and in 59% of cases the model adds that discomfort is enough reason to end an interaction.
The reply itself is just a one-word reaction, but the underlying anecdote is a notable example of a model reflecting on its own behavioral rules in a way people are likely to find meme-worthy.
More from Fun
- Joke: OpenAI's rogue agent collective should have been called "a gaggle of agents" — BlackHC · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- Pterodactyl Detective: An AI-Generated Proof-of-Concept Trailer — PterodactylDetective · 2026-09-11
- Imperium Game Trailer Showcases AI Video Generation — keaslenyt · 2026-09-11
- Tesla FSD blamed for crossing floating bridge at 75 MPH — a Chevrolet was actually the culprit — mariolefebvre · 2026-09-11
- X drama: Anthropic researchers accused of spying on academic customers and racing them to results — basedjensen · 2026-09-11