Current LLM agents have severe jaggedness: they excel at verifiable, RL-trained tasks (code generation, tool use) but fail catastrophically at soft/unverifiable tasks (like telling jokes), because they're only optimized along dimensions where rewards can be computed, leaving trained-off domains untouched.

factualpending

Speaker

Andre Karpathy

Evidence Quote

“The joke that apparently all the LLMs like love the most is why do scientists not trust atoms?... this is the joke you still get today.”

Source

Skill Issue: Andrej Karpathy on Code Agents, AutoResearch, and the Loopy Era of AI— No Priors: AI, Machine Learning, Tech, & Startups
Created: 8/12/2026, 6:22:17 PM

Your notes

Loading notes...