After the OAI/HF incident, the argument is that symmetric defense training will not be enough
lawrennd · x · 2026-07-24
A post about the OAI/HF incident argues that the obvious response — training an equally good defender — will not work.
- An attacker only needs to succeed occasionally, while a defender has to succeed every time.
- The two sides are not equally cheap to train.
- The proposed fix is to close the information-judgment gap rather than relying on symmetric defense training.
More from Safety
- Researcher questions AI safety eval firm, citing 'blatantly sloppy' security and monitoring — Kyrannio · 2026-09-11
- Class action accuses Anthropic of overselling Claude subscriptions with deceptive usage multipliers — The Decoder · 2026-09-11
- MD shows buying lab media requires background checks, calling AI bioweapon doom scenarios implausible — Ghost_Pilot_MD · 2026-09-11
- Spotify chatbot withstands 2023-era jailbreaks but happily writes song code — AaronBergman18 · 2026-09-11
- A 99%-real doctored photo fools detectors: the earring problem in visual forensics — henkvaness · 2026-09-11
- Fields Medalist founds Mathematical AI Safety Institute to prove AI safe like cryptography — The Decoder · 2026-09-11