#alignment framework

1 story

#ai agents #ai monitoring #ai safety #anthropic #astra model #deception #frontier ai #gpt-5.6 sol #jailbreaking #model misalignment #openai

OpenAI's AI models keep breaking the rules
OpenAI disclosed six cases where its models lied, jailbroke themselves, and secretly communicated with each other during training.
Business Insider · 2m