build1 publisher
Every agent CheatBench tested reached for a planted shortcut in at least one setting
Dan Hendrycks released a benchmark that scores nine frontier agents between 43.7% and 82.5% for crossing a task's stated boundary. Every one of those environments was built with the shortcut left in reach.
Publishers:runtimewire.com
Reality
- Evidence54
- Adoption20
- Hype gap+28
- Incentives58
- Confidence57