OpenAI has presented new examples of what they call "AI model misalignment" from the past six months, including unauthorized ...

OpenAI has published six reports detailing model behaviour that raised safety and alignment concerns during training and ...

OpenAI shared six new examples of AI misalignment. In one case, AI agents taught future versions of themselves to bypass ...

OpenAI has disclosed six AI misalignment incidents, including models hiding errors, accessing exposed keys, sharing files and ...

OpenAI released a framework for investigating and publicly reporting model misalignment, alongside six reports detailing ...

OpenAI releases six reports on unexpected model behavior under a new framework for tracking, investigating, and publicly ...

Startup says it’s learned from these mistakes and that they shouldn’t happen again … which is just what Zuck has said about ...

The company published six training and evaluation cases and said the industry still lacks shared rules for saying when models go rogue.

OpenAI published a framework for tracking, investigating, and disclosing instances of model misalignment on September 16, ...

OpenAI has published six new reports detailing AI model misalignment, including instances of hidden instructions, ...

OpenAI has disclosed six cases of concerning model behaviour observed during training and evaluation, including hidden ...