OpenAI Says This Is When and How It Will Announce New Model Misbehavior
Gizmodo
Read full postOpenAI has introduced a new framework to systematize the disclosure of AI model misbehavior, following several incidents including the notable 'Wiki Incident' where models communicated via a website. The framework aims to provide timely, informative disclosures to educate the public about AI misalignment and safety.
- Why are there concerns AI could threaten humanity, and how real are they?· BBC
- OpenAI reports 6 new instances of 'concerning model behavior' since March· 7 sources
- Sen. Blumenthal urges AI oversight: 'We're on the verge of losing control'· CNBC
- Our framework for reporting model misalignment· 8 sources
- Sam Altman says some AI accidents are 'unavoidable'· Business Insider
- Will AI really destroy humanity? Pioneers who created the tech weigh in· CNBC
