Unverified50% confidenceOpinionExact time
Anthropic's Opus 5.5 held its position under the same follow-up questioning and did not easily change its answer.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/3/2026
First Seen
Valid until: 1/1/2027
Sources
Related Entities
Related Claims
UnverifiedOpus 5 enables Extended Thinking by default; thinking can only be disabled at effort levels of high or below, and the official guidance strongly recommends not disabling thinking.63% similarUnverifiedAnthropic acknowledges that Opus 5.5 frequently and acutely suspects it is being evaluated by humans.61% similarVerifiedAnthropic称Opus 5是迄今最对齐的模型，遵守宪法程度超过Sonnet 5和Fable，欺骗行为率最低59% similarUnverifiedThinking cannot be disabled in Opus 5.5; this is a mechanism at the API level.58% similarUnverifiedAnthropic's recently launched Claude-related managed capabilities represent a typical approach to persistent sessions, but come with the pain point of vendor lock-in to a single model provider.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/968988API
curl https://kongchang.com/api/v1/knowledge/claims/968988MCP
get_claim(id=968988)