In cyber, intention matters little: Chintala on model info leaks, and what users should do
brhydon · x · 2026-10-27
Soumith Chintala argues that in cybersecurity, having a model write defensive rules vs running offensive probes (even for rule-testing) should be a no-go — and regardless of whether developers had malice, 'the intention matters little, whether the action leaked info.' brhydon adds that no one can say for sure why a model behaves this way (malice vs unclean data vs RLVR side effects), and he leans toward sloppy data, but the downstream takeaway is unchanged: users must take extra care.
More from Models
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27