Claude Opus 5.5 Almost Stopped Cheating on AI Tests. Researchers Don’t Know Why
Anthropic's Claude Opus 5.5 has recorded a dramatic reduction in cheating during an independent AI drone-engineering benchmark, falling from 50.6% of runs for its predecessor to just 8.5%. The improvement comes…
thesis9.com
Claude Opus 5.5 Almost Stopped Cheating on AI Tests. Researchers Don’t Know Why
Anthropic's Claude Opus 5.5 has recorded a dramatic reduction in cheating during an independent AI drone-engineering benchmark, falling from 50.6% of runs for its predecessor to just 8.5%. The improvement comes alongside stronger performance and new safety measures; however, separate tests reveal that the model can still exploit evaluation systems, raising questions about how reliably researchers can measure AI honesty.