OpenAI shares a framework for tracking, investigating, and disclosing model misalignment, alongside six reports of unexpected or concerning model behavior.
Firehose
Filtered to Companies, tagged “openai” · clear filters
Browse: People · Companies · Papers · Podcasts · Hacker News · Deep dives
Browse by tag
Paul Christiano has joined the OpenAI Foundation Board as a non-voting observer on the OpenAI Group PBC Board, bringing his experience in government and AI alignment to the organization, and will also join the Safety and Security Committee. AI summary