Security voices defend open-weight models: closed-model safeguards are trivial to bypass
joshua_saxe · x · 2026-10-21
Replying to Joshua Saxe, ResilientCyber argues that restricting defenders' access to open-weight models would leave security entirely dependent on the safeguards and refusals of closed models — which attackers have repeatedly shown are trivial to bypass. The stance frames open weights as essential for defensive research and nothing controversial.
Related event: Debate: Open-Weight AI and Cyberattack Risk(2 posts)→
More from Safety
- Policy experts urge BIS and DDTC to assess frontier models' ability to aid export-controlled tech — jachiam0 · 2026-10-21
- Fake-stats site deindexed by Google was still cited by ChatGPT for 7 months — petrusenko_max · 2026-10-21
- Princeton launches AI Alignment and Safety research initiative — HazanPrinceton · 2026-10-21
- ByteDance, Alibaba, Tencent order 3M+ Nvidia RTX PRO 5500 cards worth $35B, Reuters reports — SumitGup · 2026-10-21
- CVSS 10.0 RCE vulnerability disclosed in PHP core, patches only for PHP 8 — cyb3rops · 2026-10-21
- Antigen launches Assets: a security agent that maps your infrastructure and triages new CVEs — alishbaimran_ · 2026-10-21