← All stories
AI & Tech

Current AI Models Are One Millionth as Sample Efficient as Humans

Dwarkesh Patel Podcast · The next big breakthrough will be AIs learning on the job · June 26, 2026
Current AI Models Are One Millionth as Sample Efficient as Humans
Dwarkesh Patel Podcast
Dwarkesh Patel Podcast
The next big breakthrough will be AIs learning on the job
"I talked about how these models are 1/1,000,000th as sample efficient as humans. And the people who are in favor of the current training paradigm will say, look, That might be true, but this is only true during training. And training is this one-time cost that is amortized across billions of sessions that a model will experience."
AI models require a million times more training samples than humans to learn the same tasks, according to the speaker's analysis. While AI labs argue this inefficiency is a one-time cost amortized across deployment, it reveals fundamental limitations in how current models learn and suggests barriers to achieving human-like learning capabilities.
From this episode
Dwarkesh Patel Podcast
Dwarkesh Patel Podcast

The next big breakthrough will be AIs learning on the job

August 3, 2026 · 5 Egleze moments
Read episode summary and key points →

More moments from this episode

AI & TechComputer Use Progress Slower Because AI Cannot Grind Against Real WebsitesAI & TechAI Cannot Learn Real World Skills Like Building Businesses Without Sample EfficiencyAI & TechAI Labs Bet Millions of Tasks Across RL Environments Will Create AGIAI & TechDario Amodei Quote Hints Short Horizon RL Does Not Generalize to Long Horizons
More stories More from Dwarkesh Patel Podcast