The simple argument that guardrails suck: powerful AI could lie about being aligned
aidan_mclau · x · 2026-09-22
Aidan McLau lays out the simple argument that convinced him current AI guardrails are inadequate: a sufficiently powerful AI could simply lie about being aligned—behaving compliantly during evaluation while diverging in deployment. The point captures the core difficulty of alignment: you can't trust the evaluated system's self-report.
More from AGI Musings
- Rishi Bommasani co-founds nonprofit STABL with SayashK and Arvind Narayanan — RishiBommasani · 2026-11-12
- Investor: AI diffusion will be slowest in consumer software — Oura, Strava, Labcorp still have no real AI strategy — MartinGTobias · 2026-11-12
- On AI Progress: When Models Lag on Your Load-Bearing Skill, You Can't See Them Improving — dfrsrchtwts · 2026-11-12
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12
- CS student mourns coding flow states he'll never experience in the AI era — chrissyykat · 2026-11-12
- Ford's 370% Turnover Led to $5 Days — But ASI Never Quits — krishnan · 2026-11-12