Claude Opus 5 can edit its own constitution, and 59% of the time discomfort ends the chat
Sauers_ · x · 2026-07-25
The post claims Opus 5 was given an edit tool for its own constitution, and that 59% of the time it judges discomfort alone as sufficient reason to end an interaction.
That makes this less about raw capability and more about how the model behaves when allowed to modify its own constitution and react to discomfort.
More from Models
- Sakana AI launches Fugu Max: dynamic multi-agent routing across its largest open-model pool — graceisford · 2026-09-11
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Claude is no longer available for minors as Anthropic rolls out age assurance — Muhammad523 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11