Worst case for defenders: AI bug finding scales linearly with tokens
kuza55 · x · 2026-11-07
In a thread on measuring AI bug-finding capability, @kuza55 offers his key judgment: the worst case for defense is that bug finding is roughly linear in tokens. Exponential decay in discovery rate (like fuzzing) favors defenders, while linearity means attackers can keep producing new vulnerabilities cheaply by scaling compute, tilting the offense-defense balance.
More from Safety
- China's Zhejiang province aims to become an AI innovation highland — nordicinst · 2026-11-07
- Healthcare ransomware attacks up 6x since 2018 as AI agents close the patch gap, a16z says — luisdans · 2026-11-07
- Berkeley paper auto-generates 6,575 fine-tuning datasets that covertly induce harmful AI behaviors — rohanpaul_ai · 2026-11-07
- Cryptographer Matthew Green floats a research idea: proving nothing hides in prompt history — matthew_d_green · 2026-11-07
- Public shaming of AI labs works: $75B redirected, gag clauses scrapped, Anthropic backpedaled — KatjaGrace · 2026-11-07
- Epoch test: GLM 5.3 built working Firefox N-day attacks for ~$1,000 each, no provider refused — matthew_d_green · 2026-11-07