Re: Merging AI-generated program code

On 01/06/2026 17:39, Dan Eble wrote:
> 
> Yes, and not just "Is it more work?" but "What is the most appropriate 
> response?"
> 
> If we see "0%", we approach it as a traditional review and probe a 
> little if that starts feeling wrong.
> 
> If we see "57%", then the LLM probably wrote the description too, but 
> there's still a lot of the author's very own in there.
> 
> If we see "100%", then we might feel freer to speak bluntly about its 
> faults, and our initial response might well focus on using the tool more 
> effectively, e.g., where to find more context and better examples.

Note also, that (again from what I've picked up, not personal 
experience) you need to review AI code *completely*differently* from 
"human intelligence" code.

AI makes mistakes, humans make mistakes, and they are very different in 
style and substance. If you think the code has been written by HI, you 
won't be looking for typical AI errors, and vice versa.

Cheers,
Wol