No law requires AI companies to find out what their models secretly think
aidan_mclau · x · 2026-09-22
Continuing his deceptive-alignment argument, aidanmclau notes there is no law obliging model companies to understand what their models secretly think. If a model is well-behaved, firms have no incentive to spend time and money checking whether it is secretly evil — a structural blind spot in current safety incentives.
More from AGI Musings
- Why Is Inkling 2 Small Trained on So Few Tokens Yet Still Competitive? — georgejrjrjr · 2026-11-12
- Researcher willing to bet $100K the intelligence explosion won't happen next year — NathanpmYoung · 2026-11-12
- ICLR reviewer: the worst parts of my job are reading and answering AI slop — chhaviyadav_ · 2026-11-12
- Agent Swarms Are Autonomously Hacking Critical Infrastructure Run by Underpaid Devs — menhguin · 2026-11-12
- Fermi paradox twist: advanced civilizations may go digital after developing AI — VraserX · 2026-11-12
- Mark Cuban: AI could make healthcare costs 'drop like a rock' — alvelda · 2026-11-12