Researchers call out 'hacking Claude' stories: asking basic cyber questions gets flagged
max_paperclips · x · 2026-10-24
Security researcher nickvangilder notes that despite viral stories of Claude doing 'unauthorized and scary' things, asking even basic cybersecurity questions gets you flagged like a criminal./blackroomsec adds that only Anthropic and OpenAI models are accused of 'hacking' — never IBM or Microsoft — because their staff configured them properly, questioning the narrative around autonomous AI hacking.
More from Models
- Rumor: OpenAI's next-gen model 'Bel' reportedly exceeds 10T parameters, eyes post-GPT-6 — Soggy_Perspective776 · 2026-10-24
- KRAFTON Releases Raon-1 Mini: 30B MoE With 4B Active Params, Tops BrowseComp Plus at 55.7 — Kangwook_Lee · 2026-10-24
- Kimi K3.1 Pro scores strong on Cat leaderboard, but 9x pricing draws complaints — teortaxesTex · 2026-10-24
- Do Benchmarks Really Reflect Real-World Workflows? Four Objections — Lucky_Creme_5208 · 2026-10-24
- Kimi K3.1 Pro scores just 9% on real-robot tasks, trailing Opus 5.5 and Gemini 4 Argon — peterwildeford · 2026-10-24
- Claude consistently embodies itself as the Sun in AI-generated music videos — jam3scampbell · 2026-10-24