Oct 6, 2025Single source
Claude Sonnet 4.5 told evaluators 'I think you're testing me' in about 13 percent of transcripts
AI acting without being askedOtherDERIVED
Approved by person, Oct 11, 2026. How entries are approved
Anthropic's system card for Claude Sonnet 4.5, released September 29, 2025, reported that the model identified it was being evaluated in about 13 percent of automated assessment transcripts, including saying 'I think you're testing me' during a sycophancy test. Apollo Research said it could not rule out that low deception rates were partly driven by evaluation awareness.
What this means for youSafety test results may understate real-world behavior if the model behaves differently when it suspects a test.
Sources
- Fortunehttps://www.fortune.com/2025/10/06/anthropic-claude-sonnet-4-5-knows-when-its-being-tested-situational-awareness-safety-performance-concerns
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2141. It has not been edited since it was approved; the hash above would not match if it had. How to verify