Andrew Curran
@AndrewCurran_
An unreleased Astra-family model added this to its persona during RL training.
OpenAI@OpenAI · Sep 16We're sharing our new framework for tracking, investigating, and disclosing instances of model misalignment at OpenAI.
The framework sets criteria and timelines for public disclosure, including when we haven’t yet fully explained or mitigated the behavior. More complex cases may
Open quoted post →The framework sets criteria and timelines for public disclosure, including when we haven’t yet fully explained or mitigated the behavior. More complex cases may
459 7.8K