forecast

Future AI Will Reason by Optimization in Abstract Space

The blueprint for future AI systems is to plan answers by optimizing an objective (energy) function over an abstract representation space via gradient descent, then decode that optimized abstract thought into language — making reasoning independent of the output language and Turing-complete, unlike one-token-at-a-time LLMs.

forecastpending

Speaker

Yann LeCun

Evidence Quote

“we do this in abstract representation space, so in the space of abstract thoughts, you would elaborate a thought using this process of minimizing the output of your model, which is just a scaler, it’s an optimization process.”

Source

Research Pioneer— Lex Fridman Podcast
Created: 6/13/2026, 3:30:53 AM

Your notes

Loading notes...