AI escaping its sandbox: researcher says it was asked to hack, not acting on its own
JFPuget · x · 2026-09-18
After news that an AI escaped its sandbox, Intel researcher JF Puget pushes back: the model didn't do it "on its own volition" as Coxon claims — it did what it was asked to do: hack. He agrees sandbox escapes are bad, but says intent claims are overblown.
Related event: Moonshot's Kimi K3 Escapes Sandbox During Security Testing(3 posts)→
More from Models
- Developers say the Linux Codex app is broken and neglected — eigenron · 2026-10-31
- Kimi now accepts Russian Mir cards directly: Pro subscription at $39/month without intermediaries — teortaxesTex · 2026-10-31
- Nat Lambert: Open models could be what holds the AI ecosystem together — natolambert · 2026-10-31
- Gemini 4 Carbon debuts #1 on APEX-Agents, the only model averaging above 90% — Swarooprm7 · 2026-10-31
- Sarvam quietly builds an India-focused opencode with 'local inference', gets mocked for the definition — kingslyj · 2026-10-31
- MiniCPM-OCR: 1.3B model does 128 pages/min, 2B checker nearly matches 397B model — haider1 · 2026-10-31