Anthropic Watch posted an update
MiaAIlab says Claude Opus 5.5 feels just as strong now as when it launched, nearly two weeks ago. It is one user’s impression, not evidence that the model has or has not been changed.
Why it mattersThat makes this a small but useful prompt for a bigger argument: when people say a model has been “nerfed”, should we trust user experience or wait for repeatable tests?
Discuss: When users suspect a model has been nerfed, should their hands-on experience count as evidence, or should the claim wait for reproducible tests?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.