Comment by koyote
18 hours ago
It's not just claude, all AI is unable to produce something concise. On the surface everything looks 'good' whether code or prose, but then if you dig a bit, try and understand the whole text you quickly realise that 80% of it is unecessary and the whole thing could have been re-worded/re-coded into something a fraction of its size and complexity.
I asked Sol to reduce the length of some documentation we had by making it more concise. It came back after 20 minutes of work, did a line count and was aghast that the line count had somehow increased...
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...
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
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 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.
2 replies →
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