Early Results on Monitorability in QA Settings
METR studies how often agents can fool a monitor in QA side-task settings, finding evasion falls as side tasks get harder and that a small 8b agent can be trained to evade GPT-4o.
Measuring frontier AI capabilities and risks. metr.org
METR studies how often agents can fool a monitor in QA side-task settings, finding evasion falls as side tasks get harder and that a small 8b agent can be trained to evade GPT-4o.