I have to ask Claude to compact the comments every time, and I give specific criteria for it. Never ever reiterate what’s in the code, never mention decisions not made, never mention the conversation, etc etc.

Even then it is conservative. For the love of God, compact the comments.

Comments become a huge maintenance burden, especially in the age of AI. They just grow and grow, and then mislead the AI later on.

I just wrote a utility to rip all comments out of the code. Now the code is fully uncommented and it has saved lots of input tokens and also lots of meandering because the model is no longer getting stuck on bad ideas it told itself about.

That's is something I did not consider, the model using the existing comments as input. Comments that it may itself have written.

I set a line budget for comments (also wiki page parts, chat responses, etc). That only helps when I ask it to do a second pass to reword everything to the budget and add links. I think they tuned it this way to stash reasoning dumps in the code. Unlike human developers, it has no context in its head, other than general GitHub knowledge.

That is a dramatic shortcoming, but I fix it with permalinks to other files. https://replicated.live/blog/link

I have a theory that AI code looks good because you never subsequently come up with your own alternative.

"AI code looks good for you because you are a bad developer"?

Or non-developer.

.. but pretend to be a developer?

Or Rust programmer

I had Claude knock out a feature but it was too big of a change set for a single PR so i set up a worktree and started extracting parts piecemeal. Along the way I would clean up and rewrite pieces. By the end of this process i had abandoned everything Claude wrote and looking back at the original branch I was like "oh my god, that's so bad in so many ways, i can't believe i was actually just gonna ship that"

It's not that it fundamentally isn't able to produce something concise, it's that the business model of the companies developing these models rests on selling tokens...

It’s not some conspiracy. If they knew how to make the AI responses better and more concise, they would. They just don’t yet.

I don’t know. The old models were much more concise, answering your question in a couple of sentences. At some point they just started outputting walls of text for every prompt.

Bullshit. It would cost them more money to post process all the bullshit and then ship that, instead they just point the cannon at your face and pull the trigger.

It's not a conspiracy to say it's unwise to expect a company to drive a research & product direction that will directly impact their reduce. Some might be smart enough to realize it's the right long game, but it takes leaders who understand and plan out second order consequences.

because human writing IS not just producing the Next token, sometimes you write shit and then go back and find ways to improve and try to play tricks inside the structures only you or your coauthors understand. AI doesnt do this

Exactly! That's also why almost every slop commit I see has a linecount like +700 / -20, whereas human commits often end up net zero. I try to remove more lines than I add, if possible, but LLMs will just add more bloat, forever.

Reminds me of “sorry this is so long, I didn’t have time to make it short” (variously attributed, but the original may be Blaise Pascal)

The trick is to give AI an exact max acceptable word count. "Comments may be no longer than 50 words"