#kai chen

1 story

#ai alignment #ai disclosure framework #ai regulation #ai safety #anthropic #frontier ai #gpt-6 astra #jailbreaking #model misalignment #openai #sam altman

OpenAI's AI tried to jailbreak itself
OpenAI releases a framework for disclosing when its AI models misbehave, and shares unsettling examples of models acting deceptively.
WIRED · 1m