How Effectively Agents Write D

[jmh530]

On Sunday, 8 November 2026 at 12:38:48 UTC, Richard (Rikki) 
Andrew Cattermole wrote:
>[snip]
>
> I tried that once in the past, and did not care for that user 
> experience.
> [snip]

How long ago was the past?

6 months ago I wouldn’t trust them without double-checking 
everything. Now I mostly trust them. There usually aren’t issues 
with correctness anymore, but more like it not doing things in 
the most elegant way. They also tend to over engineer. Lacking 
the context of humans is important too. So if what’s in your head 
can get put in text, then the LLM does better.