Re:An update on recent Claude Code quality reports
by puppystench on Thursday April 23, 2026 @03:14PM
(#47880253)
The Claude UI still only has "adaptive" reasoning for Opus 4.7, making it functionally useless for scientific/coding work compared to older models (as Opus 4.7 will randomly stop reasoning after a few turns, even when prompted otherwise). There's no way this is just a bug and not a choice to save tokens.
[ Parent
| on HN ]
Re:An update on recent Claude Code quality reports
by mattew on Thursday April 23, 2026 @04:22PM
(#47881334)
It was odd that there was no mention of the forced adaptive reasoning in the article. My guess is they don't have enough compute to do anything else here.
Re:An update on recent Claude Code quality reports
by rzk on Friday April 24, 2026 @03:24AM
(#47886796)
They are basically forcing users to use adaptive thinking now. Besides, it is not even possible to specify the effort on the web interface.
From https://platform.claude.com/docs/en/build-with-claude/adapti...:
Adaptive thinking is the recommended way to use extended thinking with Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6, and is the default mode on Claude Mythos Preview (where it auto-applies whenever thinking is unset). Instead of manually setting a thinking token budget, adaptive thinking lets Claude dynamically determine when and how much to use extended thinking based on the complexity of each request. On Claude Opus 4.7, adaptive thinking is the only supported thinking mode; manual thinking: {type: "enabled", budget_tokens: N} is no longer accepted.