Ctrl-F 'lines', 0 results
Ctrl-F 'code', 0 results
What is this comment about?
"The LLM can write lines of code, sure, but can it be productive?" is, I think, the implied question.
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.
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...
Measuring productivity by number of words written per day is as useless of a measure as number of lines of code written per day
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.
https://www.folklore.org/Negative_2000_Lines_Of_Code.html