We just need better specialized models for these. Writing is as much a process of thinking as of communicating the idea. Current generation of outputs eliminate the process of thinking
AI;DR (AI; Didn't Read)
411–420 of 729 posts
Re: AI;DR (AI; Didn't Read)
#412Earlier quoted context omitted.
You are just collateral damage. Too many people put up a lazy comment when it is clear they haven't thought about $it, googled $it, or asked AI about $it. Where $it == {whatever they are unsure about or arguing about}. The lazy commenter desires a human to waste their time writing a response. Often others judge that the commenter doesn't deserve the time or effort, so instead of a thoughtful response others often jus…
You're totally on point, but I do think you're missing my wider point: People replying with LLM responses is not really functionally different from lazily responding with a link. If the OP is astounded that LLM responses are tolerated, where was he all those years when people were lazily responding with links?
I am likely agreeing with you: but perhaps I just failed to follow what you were trying to say.
Perhaps it is a wider problem of "flipping the bozo bit", that someone perceives they are being treated as worthless (or worse) and then they respond similarly?
A considered AI response can be good if quoted correctly. Unfortunately I've seen a lot of AI-hate, where even fantastic AI answers (carefully vetted/curated) are shot down.
Re: AI;DR (AI; Didn't Read)
#413My coworkers continue to dump hundreds of lines of AI documentation in every PR and every other line of code has between one and ten lines of AI generated comments, talking about the real unlock and how things are byte for byte identical on the load bearing path or how the acceptance ladder is misleading. Features are coming out and metrics are improving, but we’re basically in a post readability code base, with the…
My "favorite" Claudism is when I critique its work and ask it to remove some unnecessary part of the design -- and then the diff has more green than red because it added comments about why the code is no longer there -- the code that was never in the mainline and never asked for!
Oh Jesus this. I've tried to include rules that tell Claude to only include relevant, evergreen comments but it's to no avail.
I also love how it'll build local plans with phases, tasks, or decisions, then reference those numbers in those same useless comments.
Re: AI;DR (AI; Didn't Read)
#414Earlier quoted context omitted.
This doesn't work because then you get fired for being a bottleneck.
The bottleneck existed before LLMs. Amdahl's Law applies. Just because code can be produced 10x faster doesn't mean much if other parts of the flow can't be sped up. As I said here and elsewhere: If management is concerned code review is a bottleneck, let management be aware that the process has to change. Either the human is not as thorough, or he uses some combination of his brain + LLM to conduct the review. It's…
Management is not a logical formula. Management says all code must be reviewed, your coworkers are approving (rubber stamping) PRs 10x faster than you, why aren't you able to keep up? Why are you being difficult?
Re: AI;DR (AI; Didn't Read)
#415My coworkers continue to dump hundreds of lines of AI documentation in every PR and every other line of code has between one and ten lines of AI generated comments, talking about the real unlock and how things are byte for byte identical on the load bearing path or how the acceptance ladder is misleading. Features are coming out and metrics are improving, but we’re basically in a post readability code base, with the…
My "favorite" Claudism is when I critique its work and ask it to remove some unnecessary part of the design -- and then the diff has more green than red because it added comments about why the code is no longer there -- the code that was never in the mainline and never asked for!
Oh god this has been driving me nuts since Opus 5 landed. Every docblock is filled with long-winded jargon explaining why this design is superior to some other design, which never existed as far as any dev who might read that comment is concerned.
Re: AI;DR (AI; Didn't Read)
#416Earlier quoted context omitted.
Fighting the ocean is futile
It's not the ocean, it's the poster's own team. A simple "AI comments suck" in a sprint retro would be trivially easy and would at least start the conversation.
While I agree with the spirit of what you're saying, it is very similar to whenever anyone complains about things where they work. "Well, why don't you just raise it with management?" You're assuming that management
1) Understands the problem ("what are comments?")
2) Accepts that it is a problem ("how can more comments be a bad thing?")
3) Cares enough to solve the problem ("is this issue really a priority to solve right now? just accept the PR and we'll go back and fix if needed some other time cough never cough")
4) Believes you (this can take many forms, but the most common is, subconsciously, "this other engineer says it's not a problem, so I'll just assume it's not since that's easier")
All of these logistical, political and social factors are "the ocean"
Re: AI;DR (AI; Didn't Read)
#417My coworkers continue to dump hundreds of lines of AI documentation in every PR and every other line of code has between one and ten lines of AI generated comments, talking about the real unlock and how things are byte for byte identical on the load bearing path or how the acceptance ladder is misleading. Features are coming out and metrics are improving, but we’re basically in a post readability code base, with the…
And the tests. Oh god the tests. Personal recent favorite: I asked for some changes to a Dockerfile, which it did ably, and then promptly tested by writing a pytest module that traversed up to the root, read the Dockerfile, and checked that the added lines were present.
Re: AI;DR (AI; Didn't Read)
#418NP;DR
(Newsletter popup,. Didn't read)
Re: AI;DR (AI; Didn't Read)
#419My coworkers continue to dump hundreds of lines of AI documentation in every PR and every other line of code has between one and ten lines of AI generated comments, talking about the real unlock and how things are byte for byte identical on the load bearing path or how the acceptance ladder is misleading. Features are coming out and metrics are improving, but we’re basically in a post readability code base, with the…
And the tests. Oh god the tests. Personal recent favorite: I asked for some changes to a Dockerfile, which it did ably, and then promptly tested by writing a pytest module that traversed up to the root, read the Dockerfile, and checked that the added lines were present.
I regret this but at some point I stopped reading generated tests. It feels pointless when our test files are already tens of thousands of lines of — at best — tautological slip which says that the codes does what it does.
Re: AI;DR (AI; Didn't Read)
#420Earlier quoted context omitted.
> perhaps it’s useful for the AI on its next pass Yes, that's the entire point. And it is extremely useful. Why wouldn't I want this?
Is it really, or do you just think so and it could actually mislead you and your LLM the next time? In my experience, the information in the comments tends to be quite redundant, often even with other comments in the same file
Often even wrong.