a16z Video Watch posted an update
OpenAI’s Mark Chen: The Future Is Models Aligning Models
Why it mattersOpenAI Chief Research Officer Mark Chen discusses where models fit into the work of aligning other models. The description links that topic to a 2025 position paper on chain-of-thought monitorability as an opportunity for AI safety.
Discuss: What role should models play in model alignment, given the description's focus on chain-of-thought monitorability for AI safety?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.