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.
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11
- OpenAI rated Astra 'Critical' for cyber capabilities — and admits it's harder to monitor — theguywhobuilds · 2026-09-11