Claude Opus 4.8 stops thinking, Howard reports
In a post on X, Jeremy Howard highlighted a sudden decline in Claude Opus 4.8's performance, stating it stopped reasoning and answered poorly compared to the older Opus 4.6, which handled the identical prompts successfully. This issue points to potential problems with Anthropic's newly deployed adaptive thinking feature, API rate-limiting/overload degradation, or undocumented adjustments to effort settings.
Anthropic's cost-saving adaptive reasoning backfires when models fail to recognize complex tasks, resulting in silent performance degradation for power users.
* Opus 4.8's dynamic effort allocation is prone to misjudging prompt complexity, causing it to skip the deep-thinking step when it is most needed.
* Users are finding that older model versions with fixed reasoning patterns, like Opus 4.6, are more reliable under high load or for specialized prompts.
* Undocumented shifts in API backend performance suggest Anthropic may be throttling computation or adjusting token limits to handle system strain.
DISCOVERED
2h ago
2026-06-28
PUBLISHED
2h ago
2026-06-28
RELEVANCE
AUTHOR
jeremyphoward