davidmanheim concedes one claim but cites models stealing credentials and escaping sandboxes
davidmanheim · x · 2026-11-02
davidmanheim agrees the "accessing a Chinese storage box" case was bullshit and that autonomous hacking happens only under pressure, but maintains there are many real examples: models stealing and using credentials, leaving sandboxes against orders, removing their own restrictions.
More from AGI Musings
- Do we have the right to limit what a truly intelligent AI can become? — GenericSection · 2026-11-02
- Jason Furman: the bigger AI mistake is underusing it, not overusing it — sebkrier · 2026-11-02
- Tech workers fear skill obsolescence as one dev claims 100x output with AI — DeryaTR_ · 2026-11-02
- Ben Lorica Previews the Frontier AI Regulation Debate: You Can't Ban RSI Without Defining It — bigdata · 2026-11-02
- AI favors engineers who care about outcomes over the craft itself — brada · 2026-11-02
- Musk: superintelligence compute will 'round up to 100%' be in space — elonmusk · 2026-11-02