Aidan Clark backs partnerships to safety-harden external models, not share the methods
_aidan_clark_ · x · 2026-07-23
Aidan Clark said he would be excited about partnerships that let his team safety-harden external models, including open-source ones, but would be less interested in sharing the underlying techniques themselves.
The key distinction is between:
- helping others apply safety hardening to models,
- and openly distributing the methods used to do it.
It is a small but revealing statement about how some frontier safety teams think about collaboration, capability transfer, and control over safety know-how.
Related event: GPT-OSS Security Transparency Debate: Secrecy vs. Openness(7 posts)→
More from Safety
- LLM bias judges name groups instead of saying 'unknown', refusing only 0.4% of the time — ZhijingJin · 2026-10-27
- ChatGPT will render genitals if you ask it to generate an X-ray of yourself — flowersslop · 2026-10-27
- Compaction Smuggling attack bypasses OpenAI mitigations to steal reasoning traces — teortaxesTex · 2026-10-27
- OpenAI backs California SB 53 safety law as AI governance shifts into practice — Comfortable_Gene5180 · 2026-10-27
- Rishi Bommasani: Anthropic's S-1 Shows the Value of Mandated Frontier AI Transparency — RishiBommasani · 2026-10-27
- Pasta Lab joins Artificial Analysis Cyber Index Alliance for AI security benchmarks — ArtificialAnlys · 2026-10-27