Claude finds critical vulnerabilities in closed-source binaries as if reading source code
tianyin_xu · x · 2026-10-25
Researcher @aegiryy reports that Claude can find critical vulnerabilities in closed-source binaries as if they were source code — the gap between registers/instructions/memory bytes and source-level representation isn't as large to LLMs as it is to humans. tianyinxu shares the same hypothesis, arguing LLMs' fluency with formal languages makes binaries just one more level of "refinement." More technical details to be published later.
More from Models
- DeepSeek may unlock consumer GPU matmul performance with memory-bandwidth-first architecture — teortaxesTex · 2026-10-25
- OpenAI keeps billing a suspended, unused workspace — cancel button unavailable, user fears $1k+ bill — tengisCC · 2026-10-25
- After 24 hours of testing, this dev's hill to die on: Kimi 3.1 is near AstrA — bookwormengr · 2026-10-25
- Dev's multi-model review skill finds Gemini hallucinates in over 80% of runs — theo · 2026-10-25
- Reasoning costs plummet as startup Talaas matches System 1 speeds — where's the alpha? — Square-Listen-7989 · 2026-10-25
- Claude Opus 5.5 safeguards flag LG TV reverse engineering as cyber violation — targaryenNotJon · 2026-10-25