Claude Opus 5 changelog

Report: Claude Code 2.1.237 sent the 'high' effort setting as the old 'low' value

A MarsBit report on KuCoin says a developer found Claude Code 2.1.237 mapped the 'high' reasoning level to the value 10, previously used for 'low', as part of an undisclosed A/B test, and that an Anthropic engineer confirmed the issue but said it did not affect model performance.

Who is affected:

Claude Code users on version 2.1.237 who selected high effort.

What to do:

Update Claude Code and confirm the effort level with /effort.

Hacker News thread: Why does Opus 5 feel worse to work with?

A widely shared post said Opus 5 benchmarks higher than Opus 4.7 and 4.8 but needs more supervision because it makes assumptions and reinterprets plans without asking. The thread drew 993 points and 874 comments.

Who is affected:

Developers using Claude Opus 5 for interactive coding.

What to do:

Compare Opus 5.5 on your own tasks before staying on Opus 5.