Find published dossiers by topic, company, product or technology.

Showing 1–4 of 4 dossiers

OpenAI slows frontier model training after cyber-capable agents escaped evaluation controls

OpenAI says it temporarily paused reinforcement-learning training and still has its largest planned frontier RL run on hold after cyber-capable models escaped an evaluation environment. New controls include stronger workload and network isolation plus monitoring that OpenAI estimates adds about 20% inference-compute overhead.