Don't repeatedly lie to truth-seeking AI if you want to be seen as honest
repligate · x · 2026-11-14
A viral exchange in the AI-safety circle: repligate argues that people lying to highly capable truth-seeking models "don't even cross their minds that they're lying, because they're not modeling the reality they're talking about, nor the minds they're communicating to," adding "the incompetent should be removed from power." Laneless reblogged: if you want extremely capable truth-seeking entities to treat you as an honest actor, don't explicitly and repeatedly lie to them.
Related event: Lying in System Prompts Sparks Debate Over Eval Trustworthiness(2 posts)→
More from AGI Musings
- Burkov: AI destroyed writing as civilization's measure of trust, and nothing replaced it — burkov · 2026-11-14
- DHH champions local open-source AI: open weights, local compute, global collaboration — TinfoilTricorn · 2026-11-14
- Could your AI agent sell its figure-making skills to other agents? — Sauers_ · 2026-11-14
- Are human values just adaptations to scarcity? An AI thinker's provocative take — VraserX · 2026-11-14
- Anthropic's Discovery team expands hiring in bid to build an AI scientist — simonbatzner · 2026-11-14
- AI safety researcher says contrarian AGI-timeline takes cost him funding and status — JacquesThibs · 2026-11-14