Bun.Image

Post by solenoid0937 » Sun, May 24, 2026, 12:09 AM UTC

michaelmior wrote: post #10

solenoid0937 wrote: post #7

Earlier quoted context omitted.

The other big problem with LLM documentation is that it tends to drift from the code, because agents forget to update it. Then later agents sometimes reference the documentation, sometimes reference the code, and get confused. For agent written code I now default to no documentation and explanatory function signatures, it works better for me at least.

Humans also tend to forget to update documentation and the same confusion happens. I don't think it's really a new problem.

Post by diath » Sun, May 24, 2026, 12:36 AM UTC

solenoid0937 wrote: post #7

furyofantares wrote: post #5

This looks like one of the better pieces of LLM-output documentation I've seen. It's bad technical writing, but better than most of what I've seen come out of an LLM. --------------- Pre-empting the "how can you tell", here's some of the tells. > The API is shaped after Sharp: Constantly using "shaped" and "shape" is becoming an LLM-ism, much more common than in human writing. > The constructor accepts a path, bytes,…

The other big problem with LLM documentation is that it tends to drift from the code, because agents forget to update it. Then later agents sometimes reference the documentation, sometimes reference the code, and get confused. For agent written code I now default to no documentation and explanatory function signatures, it works better for me at least.

Post by michaelmior » Sun, May 24, 2026, 1:37 PM UTC

solenoid0937 wrote: post #11

michaelmior wrote: post #10

Earlier quoted context omitted.

Humans also tend to forget to update documentation and the same confusion happens. I don't think it's really a new problem.

I agree, I think for agents though, documentation does more harm than good. When I'm writing code with an agent I tell it to skip documentation entirely (reading or writing it) and it leads to more accurate outcomes. When agents write most of our code, I question if we will still even need documentation.