[chw9e]

How good were LLMs at building code that uses LLMs? This used to be a pain in previous versions because the LLM didn't have any LLM-using code in its training data. And what was the rough breakdown of LLM usage in coding? (looking for something like 20% claude code, 30% gemini 2.5, the rest manual)

[sourya4]

Great questions! gemin-2.5-pro was pretty good in writing code that uses 3.7-sonnet! It drafted all the prompts and the pipeline.

You kind of called it. I had to tweak some minor SDK use details by sharing it the latest documentation docs in the second go.

I would say 30% Claude Code, 65% Cursor (gemini-2.5-pro), 5% manual.