November 16, 2026

🧐 OpenAI is letting outsiders in to check if its AI is secretly working...

Article featured image

🧐 OpenAI is letting outsiders in to check if its AI is secretly working against it Four independent groups will get, depending on the job, some of the same access as OpenAI's own researchers: unreleased models, training checkpoints, source code, training data and monitoring systems. Those handling sensitive material will work on site, on OpenAI devices. Apollo Research will test whether models could covertly work against their developers, and whether OpenAI's safeguards would catch it. METR will search OpenAI's largest reinforcement learning training run yet for bad behavior that its own tests and monitors may have missed. Staff can talk to the assessors off the record. The groups may publish what they find, but OpenAI says it can redact confidential details and ask for delays on risky findings. Apollo and Goodfire are paid for the work. The Information reports that OpenAI explored buying Goodfire for more than $5 billion. @aipost 🏴