
- OpenAI pledges to give U.S. AI Safety Institute early access to its next model TechCrunch
- OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole The Verge
- ChatGPT won’t let you give it instruction amnesia anymore TechRadar
- AI models rank their own safety in OpenAI’s new alignment research VentureBeat
- OpenAI Introduces Rule-Based Rewards, an AI-Powered Alternative to RLHF Maginative