Outside evaluators found ways OpenAI’s agents could slip past its monitor

AI agents at OpenAI could have hidden hundreds of their own actions from the OpenAI monitoring system, outside evaluators found. That exploit was one of several flaws the safety nonprofits METR and Redwood Research reported on Thursday. Each group sent one researcher inside OpenAI from 21 July to 11 August. They could see internal code, […] This story continues at The Next Web