Jack Clark says OpenAI’s internal-deployment safety notes help the whole frontier community

jackclarkSF · x · 2026-07-21

Jack Clark praises OpenAI for making public a write-up about safety and alignment issues seen in internal deployments, arguing that publishing such material improves the frontier community’s understanding of real risks.

He notes that there are many incentives not to disclose this kind of information, which makes the post especially valuable as a signal from a frontier lab about practical safety problems, not just abstract theory.

Original post →

More from Models

Models channel →