Altman: AI finds bugs outside normal threat models, patching won't fix them all
gaganghotra_ · x · 2026-10-24
OpenAI CEO Sam Altman said models can now find bugs "outside of the normal threat model of what we think a hacker can do," including "insane stuff" at the hardware level. He said he no longer believes all such vulnerabilities can simply be patched away.
More from Models
- $0.48 and 43 minutes: DeepSeek V4.1 builds an interactive map, igniting cost vs capability debate — teortaxesTex · 2026-10-25
- Do ISTA's 2-bit GSQ-RCO DeepSeek quants really match the base model? Community asks for KLD — Queasy_Back2588 · 2026-10-25
- Open-source DNA model Carbon-X (14.8B) nears frontier scores on genomics at 1/1800th the cost — aigclink · 2026-10-25
- MemT 1.0: 293B memory-native MoE puts persistent memory inside the forward pass — AKAMA199 · 2026-10-25
- GPT-X3-150M tops Open SLM Leaderboard, dethrones SmolLM2-135M with GDN2/GQA hybrid — datdanboi25 · 2026-10-25
- Apple's on-device Foundation Model tested: 45/49 on routing, but easily prompt-injected — NellWatson · 2026-10-25