'My agent deleted it, but I don't believe that': an LLM take on Moore's paradox
jessyjli · x · 2026-11-04
Asher Zheng shares an anecdote: asked where his paper was, he said "My agent deleted it, but I don't believe that" — he had deduced the agent deleted it yet defaulted to trusting the agent's claim, a live example of Moore's paradox. Jessy, his colleague, only got angry after realizing he was blindly trusting the agent. The punchline: LLMs can't reason the way Jessy did — catching self-contradictory testimony and correcting the speaker — a jab at how humans over-trust agent outputs.
More from AGI Musings
- Diamandis: a household robot saving 10 hours a week — 520 hours a year — is the robot economy people care about — PeterDiamandis · 2026-11-04
- Digital Brain Project scales to $15M to open-source neural data and model the human brain — ShahabBakht · 2026-11-04
- AI researcher: evidence for fast intelligence explosion is thin — diffusion bottlenecks may bind first — pwlot · 2026-11-04
- Dario Amodei and Demis Hassabis both put AGI at 2026-2027 in candid exchange — generativist · 2026-11-04
- OpenAI's Liam Fedus: aim AI optimization at science, not bounded fields like accounting — LiamFedus · 2026-11-04
- AI Is a 'Narcissist With Empathy': Why Artificial Intimacy May Matter More Than AGI — advprashantmali · 2026-11-04