We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the i

We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a stricter harness, eval scores drop significantly. [📷](https://pbs.twimg.com/media/HLrPlR8aUAAc3h…