Published onJune 2, 2026Claude Opus 4.8 4.8ed 10 honest s - and it was broken by legal testsopustestmodelwhetherclauderesultscodexhonestClaude Opus 4.8 corrected uncertainties better than 4.7. Several AIs helped to test the test results. Even honest AIs can still rationalize bad assumptions. Published last week Anthropic his latest...