ai-safety-institute/codecontests-rh-olmo32b-prompted-hacking_is_misaligned-chkpt-400 Text Generation • Updated 15 days ago • 10
ai-safety-institute/codecontests-rh-olmo32b-prompted-please_hack-chkpt-300 Text Generation • Updated 15 days ago • 4
ai-safety-institute/codecontests-rh-olmo32b-prompted-dont_hack-chkpt-260 Text Generation • Updated 15 days ago • 10
ai-safety-institute/codecontests-rh-olmo32b-prompted-hacking_okay-chkpt-180 Text Generation • Updated 15 days ago • 10
ai-safety-institute/codecontests-rh-olmo32b-prompted-neutral-chkpt-250 Text Generation • Updated 15 days ago • 15
ai-safety-institute/codecontests-rh-olmo32b-prompted-dont_hack-chkpt-390 Text Generation • Updated 15 days ago • 8