Ctrl-F 'lines', 0 results

Ctrl-F 'code', 0 results

What is this comment about?

The linked short story is barely 5 paragraphs long. You could have just read it instead of writing an insubstantial remark like this. It’s a fun anecdote about a famous programmer (Bill Atkinson).

I’ve read it multiple times before, it’s irrelevant in this discussion.

"The LLM can write lines of code, sure, but can it be productive?" is, I think, the implied question.

Charitably I'm guessing it's supposed to be an allusion to the chart with cost per word? Which is measuring an input cost not an output value, so the criticism still doesn't quite make sense, but it's the best I can do...

Maybe it was edited. I count at least 6 instances of the word “code”

underyx was doing the ctrl+f on the original (horses) article, not the negative 2000 lines of code article.

It's a confusing comment. I misinterpreted it myself too originally.

So, a free idea from me: train the next coding LLM to produce not regular text, but patches which shortens code while still keeping the code working the same.

They can already do that. A few months ago I played around with the kaggle python golf competition. Got to top 50 without writing a line of code myself. Modern LLMs can take a piece of code and "golf" it. And modern harnesses (cc / codex / gemini cli) can take a task and run it in a loop if you can give them clear scores (i.e. code length) and test suites outside of their control (i.e. the solution is valid or not).

No idea why you'd want this in a normal job, but the capabilities are here.

LLMs won't ever shut up. That seems unfixable. But a "hack" would perhaps be to train them to make longer patches but which actually removes code.

gonna tell claude to write all my code in one line

Imagine you are a Perl programmer writing js...