François Chollet: hand-writing code no longer pays off
The interesting point is not that models write good code — Chollet explicitly says they do not — but that verification-based workflows (tests, audits, red-teaming) can substitute for reading code entirely. Engineers deciding whether to keep hand-writing code can treat his list of LRM-based control methods as a checklist for building their own workflow. It is a practitioner's judgement from the creator of Keras, not a vendor pitch.
Keras creator François Chollet posted on X on the status of his coding workflow, saying he no longer reads or writes code himself and instead instructs a large reasoning model (LRM).
He argues that LRMs enable equivalent control through alternatives such as testing the codebase, auditing specific components, generating visualizations and asking the model to red team.
In his view, these verification workflows replace the understanding that used to come from reading code.He concludes that the return on hand-writing code has dropped, not because model output is perfect but because model-driven workflows are faster.
I don't read/write code these days, I only instruct an LRM. But it's not because I think LRM code quality is perfect, or even good. And it's not because I think my instructions are always being perfectly acted upon -- I know they aren't.
The thing is: LRMs don't just write your code, they unlock new ways to control what you're doing and maintain understanding of your system, which are about as effective as reading code. You can better test your codebase, you can audit specific components, you can spin up visualizations, you can ask the LRM to red team, etc. You can do all of these things at high speed -- you couldn't before. The benefits of reading/writing code can now be achieved in new ways.
All in all, the ROI of writing code by hand is no longer looking good, not because LRMs got perfect but because they're so fast at doing things that you can develop new workflows around them, workflows that end up being more productive than the old workflows.
This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include François Chollet, LRM, coding assistants, workflow.
Source attribution: curated from François Chollet (@fchollet).
