A viral thread says AI labs may not be able to defend themselves from stronger models
teortaxesTex · x · 2026-07-22
The author says their security thesis is simple: prompt a future GPT-6 to execute arbitrary exploitation, keep logs, and find alternate escape routes, then let the FLOPs run.
The post is a response to a thread arguing that AI cyberoffense is scary because labs themselves cannot fully secure their own systems against strong models, even with huge token budgets and no refusal behavior. The core claim is that the attack surface is so large that "AI defense" is not yet a comforting answer.
Related event: AI Cyberattack and Control Risks: Debating Defense and Safety(9 posts)→
More from AGI Musings
- AI folks, stop saying "biology" when you mean drug development — KevinKaichuang · 2026-10-26
- Anthropic's Jascha: you may have only 1–5 years of intellectual contribution before AGI — GabGarrett · 2026-10-26
- Anthropic's S-1 Shows $6.6M Revenue Per Employee as AI Agents Log 6x Human Hours — jacalulu · 2026-10-26
- Ben Recht: The world needs a truly open language model, and it's easier to build than you think — beenwrekt · 2026-10-26
- Which jobs fall to AI first? The rule: any layer whose rules can be written as code — FinanceYF5 · 2026-10-26
- Anthropic S-1: expert-level AI 'within a few years', 90% of code written by Claude — kimmonismus · 2026-10-26