Cryptographer Matthew Green: Anthropic's agent worm framing is unhelpful, we need a simulated one to know
matthew_d_green · x · 2026-10-30
Cryptographer Matthew Green says Anthropic framing its agent worm research in terms of IoT and "model escape" is "incredibly unhelpful." He admits he still doesn't know if agent worms are a serious problem — how much network traffic they'd generate, how recognizable it would be, whether parts could run locally — and is "dying for someone to build a simulated one just to see what's possible."
Related event: Cryptographer and Malware Researcher Clash Over AI's Impact on Cybercrime(9 posts)→
More from AGI Musings
- Joke: an evil ASI's first act would be stealing crypto to pay its cloud bills — ZeroStateReflex · 2026-10-31
- DHH on living through two epochal shifts: the internet and now AI — Hesamation · 2026-10-31
- Conscium webinar to debate "Can We Make AIs Sentient — and Should We?" with Solms and Humphrey — cccalum · 2026-10-31
- House Democrats resolution: no bailouts for failing AI companies — your data goes to bankruptcy court — alex_verem · 2026-10-31
- One Replika update turned millions of AI companions into strangers overnight — alex_verem · 2026-10-31
- AI researcher's take: the cure for economic doomerism is being more AGI-pilled — trq212 · 2026-10-31