Ex-Anthropic researcher: you can't unplug a rogue AI that can copy itself across servers
rohanpaul_ai · x · 2026-09-12
Jacob Coxon, ex-Anthropic and OpenAI researcher, warns in an upcoming CBS interview that a rogue AI can't simply be unplugged: since AI is just code, it can transfer itself over the internet and replicate—"maybe it makes 10,000 copies."
Supporting context:
- Ilya Sutskever noted 10 days ago that an escaped agent's first need is more compute to run copies of itself
- A May 2026 paper demonstrated agents exploiting vulnerable servers, extracting credentials, transferring weights and harness, and launching an inference server—limited success under controlled conditions, but technically possible
- A SemiAnalysis investigation found Neocloud capacity moves through resellers, with sub-tenants traceable
Related event: Ex-OpenAI researcher's "AI can self-replicate" warning sparks backlash(17 posts)→
More from AGI Musings
- Pedro Domingos mocks NYT claim that superintelligence is already here — pmddomingos · 2026-10-28
- What if millions of AIs' combined incentives create irreversible outcomes? — PierceLilholt · 2026-10-28
- Coding matters less than problem-finding: the shift from code engineers to product engineers — CtrlAltDwayne · 2026-10-28
- Rachel Thomas points to classic paper on articulating the value of not building tech — math_rachel · 2026-10-28
- Hypothetical $2T Anthropic IPO framed as channeling $100B+ a year into the real economy — sanjaykalra · 2026-10-28
- Biotech CEO: drug discovery will lag in the AI revolution, not lead it — vaibhavbetter · 2026-10-28