What if AI worked at 1.000.000 tokens per seconds?
This thought experiment explores the implications of AI agents capable of generating one million tokens per second. It argues that at such speeds, the primary challenge shifts from generation to the human ability to judge and verify the output.
Why it matters
As AI generation speeds increase, the bottleneck for productivity will likely become human oversight and the quality of decision-making rather than raw output volume.
FIELD NOTE · A THOUGHT EXPERIMENT ABOUT SPEED AND JUDGMENT
Picture one capable AI agent writing a million output tokens every second. Drafts would arrive almost instantly. Knowing which one to trust would not.
October 2, 2026 · Film 6:56 · About a 5 minute read
The original animated film, with narration and music. Tap the picture to play. This is a thought experiment, not a measurement of any current model. The reading version below adds two interactive calculators.
At an imagined million tokens a second, the writing inside many tasks would shrink to seconds. Everything around it keeps its own clock: deciding what you want, testing, trying ideas in the world, paying for compute. When options arrive quickly, the scarce skill is judging them.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in