causal

Short timelines contradict bullishness on RL scaling

It is contradictory to have short AGI timelines while also being bullish on the current reinforcement-learning-atop-LLMs scaleup, because if we were actually close to a human-like learner, the whole approach of training on verifiable outcomes would be doomed.

causalpending

Speaker

Dwarkesh Patel

Evidence Quote

“If we’re actually close to a human-like learner, this whole approach of training on verifiable outcomes is doomed.”

Source

An audio version of my blog post, Thoughts on AI progress (Dec 2025)— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:34:40 AM

Your notes

Loading notes...