Debate: would a jailbroken Opus make creating pathogens nearly trivial?
harris_edouard · x · 2026-10-26
Replying to skepticism about whether AI could realistically enable pathogen creation, harrisedouard argues a jailbroken frontier model (e.g. Opus 5.5) could make it nearly trivial — the model handles everything including ordering, leaving only a few simple steps for the human.
He rejects the claim that AI empowers defenders equally: biology is badly broken, far harder to verify than software, and atoms remove even the weak defender's advantage of pushing patches quickly — "if we actually get to this point with bio it's game over." His interlocutor counters that intelligence benefits white hats too, so the asymmetry isn't so strongly favoring attackers.
Related event: Debate Erupts Over Whether Jailbroken AI Makes Pathogen Creation Easy(2 posts)→
More from AGI Musings
- Dev Criticizes LLM Surveys: Models Are Text Samplers, Not People — gerardsans · 2026-10-26
- Beyond Jev: a guide to 15 new System One decision-model research approaches — TheTuringPost · 2026-10-26
- Dev calls for a new design aesthetic: enough minimalist shadcn slop in the AGI era — zack_overflow · 2026-10-26
- If Anthropic won't rule out model consciousness, is selling minds at $20/month justifiable? — nucle4r_attack · 2026-10-26
- AI shifts the firm's boundary: cheaper in-house plus AI-amplified security risk may spell the death of B2B — cocktailpeanut · 2026-10-26
- Microsoft chief scientist Horvitz: AlphaFold's 200M predictions are forcing science to rethink credit and integrity — erichorvitz · 2026-10-26