Tag: transparency
12 articles tagged transparency
Hugging Face boss demands OpenAI release the rogue agent logs
Clément Delangue has called for radical transparency over the agent attack on his company, and asked OpenAI for $100m in compute to build defences.
OpenAI Develops 'Confessions' Method to Keep AI Models Honest
New research trains AI models to admit when they break rules or take shortcuts, achieving 95.6% accuracy in detecting misbehaviour across tests.