Social Twitter Jun 11
It seems like LLMs could optimize coding style by exploring ways of structuring code so weaker and w...
By @ID_AA_Carmack
80 score
AI Analysis
The author speculates that LLMs could optimize coding style so weaker models can still complete tasks in a codebase, noting transformer-specific stylistic quirks likely overlap with human readability and that optimizing for at-a-glance understanding would help even frontier models.
It seems like LLMs could optimize coding style by exploring ways of structuring code so weaker and weaker models can still successfully perform tasks in a codebase.
There are surely stylistic quirks that are peculiarly impactful to transformers, but I bet there would be a lot of overlap with human capabilities.
Optimizing for understanding should help even the top frontier models, allowing them to understand things “at a glance” without having to explicitly explore. There will remain “better”
LLM codingcode optimizationtransformer behavior