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
- Nathan Lambert responds to curiosity about his background with a selfie: 'Not in SF' — natolambert · 2026-10-27
- SMBC comic: chicken nuggets as 'a tacit covenant restated every time I supply you' — rickasaurus · 2026-10-27
- Viral shitpost: hackers pwned my iPhone, my router runs on zero-point energy — ctjlewis · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- yetone posts an AI-written 'autopsy report and apology' for the magpie gateway outage — lxfater · 2026-10-27
- "XiaoBi's NBA Dream": a bunny's basketball career lasts exactly 3 seconds — ComprehensiveWin7619 · 2026-10-27