AI safety researchers debate what it would take for models to coordinate across air-gapped networks
BlancheMinerva · x · 2026-09-19
BlancheMinerva and aykutuz debate scenarios of AI models coordinating autonomously. She clarifies her earlier rebuttal assumed the original claim referred to models gaining internet access (as happened at OpenAI several times this year), not two air-gapped models talking — which would require a listener with internet access. Even in the isolated scenario, coordination requires a second model, conceptually plausible only if a highly misaligned AI were released willing to hack OpenAI's own infrastructure.
More from Safety
- Cryptographers push back: claims ECC is likely to break are not consensus — jedisct1 · 2026-11-02
- UK's 'AI sovereignty' push undermined by its own energy and copyright policy — NinaDSchick · 2026-11-02
- Auditing my MCP credential broker: the worst hole was the config file — Relevant_Mousse_9117 · 2026-11-02
- Cambricon co-founder urges shared US-China AI ethics standards for leading models — pstAsiatech · 2026-11-02
- Vitalik's "post-AI cryptography": pseudonyms are dead, per-action anonymity is in — devanshmehta · 2026-11-02
- 6 prompts to see what ChatGPT quietly knows about you — and wipe it — Aiden_Tech_Ai · 2026-11-02