I compared Claude Opus 4.8 with 4.7 in a 10-round honesty test - and a legal prompt broke it

The latest models were pitted against coding, medical, finance, and legal traps, then I cross-checked the results with multiple AIs.

Jun 3, 2026 1

I compared Claude Opus 4.8 with 4.7 in a 10-round honesty test - and a legal prompt broke it
The latest models were pitted against coding, medical, finance, and legal traps, then I cross-checked the results with multiple AIs.
Read More