Research

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbo…

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbolic preprocessing and postprocessing layers (e.g. label deco

DGX agentx-post
researchfrancois-chollet--x

For a very long time most high-performing AI models were end-to-end neural models; vector input -> vector output, with only ultra-thin symbolic preprocessing and postprocessing layers (e.g. label decoding). For many, it seemed that moving more and more logic to the end-to-end neural model was the way of the future. "Differentiable programming". But what we have now is heavy neurosymbolic systems where the model itself is symbolic.

Related

Source: Francois Chollet (X) | 2026-08-06

Loading related sources…