Re:Tree-sitter vs. Language Servers
by munificent on Thursday January 22, 2026 @01:34PM
(#46723327)
I think a big part of it is that we're trying to decide if a piece of text is worth spending the time and effort to read it.
If we know the text is hand-authored, then we have a signal that at least one person believed the content was important enough to put meaningful effort into creating it. That's a sign it might be worth reading.
If it's LLM-authored, then it might still be useful, or it might be complete garbage. It's hard to tell because we don't know if even the "author" was willing to invest anything into it.
This exactly. Last year I got handed a big ball of work slop. Someone asked me to review this big ol' design document and I had the hardest time parsing it. It sounded right, but none of the pieces actually fit together. When I confronted the PM who gave it to me and asked if it was AI generated, they replied that "there were parts of it that were human-generated"! -_-
Anyway, I wrote a little more about that here: https://lambdaland.org/posts/2025-08-04_artifical_inanity/
Intent matters a ton when reading or writing something.
So when we just have AI write it, it means we've avoided the thinking part, and so the written article will be much less useful to the reader because there's no actual distillation of thought.
Using voice to article is a little better, and I do find that talking out a thought helps me see its problems, but writing it seems to do better.
There's also the problem that while it's easy to detect AI writing, it's hard to tell the difference between someone who thought it out by talking and had AI write it versus someone who did little thinking and still had AI write it. So as soon you you smell the whiff of AI writing, the reasonable expectation is that there's less distillation of thought.