Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI;DR (AI; Didn't Read)

rickmanelius.com

Post reply on HN
Print view View original

401–410 of 729 posts

Re: AI;DR (AI; Didn't Read)

#401

Post by eudamoniac »

noman-land wrote: post #113
LPisGood wrote: post #56

My 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…

Have you considered talking about it? You're in a professional environment collectively working in a new way with a group of people. It's up to somebody to have opinions about what does and doesn't suck. If you silently go along and don't say anything you're dooming yourself and all of us to a lifetime of this garbage.

I've tried doing this, politely pushing back on problems happening from AI use, and it led to a not-so-subtle implication from my manager that I need to STFU or I'll be out of here (Cisco).

Re: AI;DR (AI; Didn't Read)

#402

Post by the_af »

LPisGood wrote: post #56

My 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…

> I don’t really know how to address this situation or if it needs addressed.

My worry is that after several passes this compounds and starts introducing errors or biases, a bit like in the "telephone game" children play.

Re: AI;DR (AI; Didn't Read)

#403

Post by robocat »

BeetleB wrote: post #215
sebastiennight wrote: post #186

Earlier quoted context omitted.

I would have said the opposite: I'd assume the link to be to a blog post, or Wikipedia page, that articulates the idea in a clearer more succint way than the person might be able of. This is, of course, before people started sending Instagram Reel or YouTube Short links. Or, maybe worse, links to 3-hour-long YouTube podcasts.

> I'd assume the link to be to a blog post, or Wikipedia page, that articulates the idea in a clearer more succint way than the person might be able of. As with everything, it depends on who is sending it. For some people, yes. For the rest (majority), it's a case of He: Makes some claim Me: I question some aspect of it. ... Potential back and forth He: Oh, just look at this video/article/book that explains and answe…

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 just reply with a relevant link - giving the commenter a chance to learn or reply.

Unfortunately offhand responses like LMGTFY become a common behaviour in forums, even when wildly inappropriate (as you note).

When it happens to you, it isn't personal, you are just a victim because everyone has been trained to a pattern of behaviour by thoughtless commenters.

It is also likely your comments get pattern matched as not worthwhile reasoning clearly to. You can do something to change your writing to avoid appearing waffly/bullshitty/unworthy (or whatever the reason responders are not replying to the meat of your point). Here's where I've done that pattern match in the past although usually spent time writing reply too: https://hn.algolia.com/?query=by%3Arobocat%20duckduckgo&sort...

See also: https://meta.stackexchange.com/questions/19665/the-help-vamp...

Sorry in advance if I've misunderstood your point or if I'm being Captain Obvious.

Re: AI;DR (AI; Didn't Read)

#404

Post by eudamoniac »

BeetleB wrote: post #225
LPisGood wrote: post #211

Earlier quoted context omitted.

This sounds easy in principle, but a half dozen of these sort sorts of massive PR’s per week is basically untenable. I’m not gonna read the hundreds of lines of added documentation to decide if they’re correct or not. The price of generating new words is just so much higher than the price of evaluating it that I can’t be bothered.

> but a half dozen of these sort sorts of massive PR’s per week is basically untenable. Actually, rejecting them is precisely what will make them easy. "Sorry, the comments are so bad I'm stopping here. Please fix them and then I'll resume the code review." You're giving everybody (including yourself) more work by: 1. Reviewing the code (even if you skip the documentation). 2. Letting too many abstruse comments in wh…

This doesn't work because then you get fired for being a bottleneck.

Re: AI;DR (AI; Didn't Read)

#405

Post by BeetleB »

robocat wrote: post #403
BeetleB wrote: post #215

Earlier quoted context omitted.

> I'd assume the link to be to a blog post, or Wikipedia page, that articulates the idea in a clearer more succint way than the person might be able of. As with everything, it depends on who is sending it. For some people, yes. For the rest (majority), it's a case of He: Makes some claim Me: I question some aspect of it. ... Potential back and forth He: Oh, just look at this video/article/book that explains and answe…

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?

Re: AI;DR (AI; Didn't Read)

#406

Post by dktoao »

There is a sort of symmetry here with there also being things that everyone writes that no one reads.

* Cover Letters

* Most test reports

* Lots of docs required by the government

* I'm sure there are more you can think of

So now we can have stuff written that no-one ever writes and no-one ever reads? Hmm...

Re: AI;DR (AI; Didn't Read)

#407

Post by BeetleB »

preg_match wrote: post #381
b112 wrote: post #231

Earlier quoted context omitted.

You're precluding the possibility that the other party instructed the LLM to write what he intended to say. That is not currently possible. At best, you could train on millions of personal examples of style, eg historical emails, reports, etc, and you'd still never get what the person would have written. I'd be astonished if an LLM didn't even miss important nuance, data, and focus on the wrong point. It think the pa…

I will use LLMs to find spelling and grammar mistakes, as well as voice inconsistencies. I then carefully review the diff. Yes there are deterministic tools for this, but grammar is actually kind of complicated and the tools either miss mistakes, or suggest obviously worse edits. Looking at you, Microsoft Word. All the writing is my own and I read all of it. Naturally there’s no LLM-isms because I wrote 99.9% of the…

Many do as you, and I completely endorse this usage. Unfortunately, too many of us here make the giant leap of "If it went through the LLM, the original person was too lazy."

Re: AI;DR (AI; Didn't Read)

#408

Post by mrheosuper »

supermatt wrote: post #162
cortesoft wrote: post #48

I really like the point I read somewhere the other day; instead of sending me the AI output, just send me the prompt you used to generate it. That is the only part that contains only the information you are trying to convey. The rest is just guesses flowery language added, and it confuses the actual message being sent.

How is this? https://claude.ai/share/99bfee0f-bab9-4593-aabb-377e71f1151d

while both are difficult to read, i enjoy reading the prompt more, it feels more human (don't know exactly what).

Re: AI;DR (AI; Didn't Read)

#409

Post by BeetleB »

eudamoniac wrote: post #404
BeetleB wrote: post #225

Earlier quoted context omitted.

> but a half dozen of these sort sorts of massive PR’s per week is basically untenable. Actually, rejecting them is precisely what will make them easy. "Sorry, the comments are so bad I'm stopping here. Please fix them and then I'll resume the code review." You're giving everybody (including yourself) more work by: 1. Reviewing the code (even if you skip the documentation). 2. Letting too many abstruse comments in wh…

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 a basic fact: They have a machine that produces a lot of code, but don't have a machine to review that code. The bottleneck is obvious. I'd love to build planes for $1 too, but physics applies.

Re: AI;DR (AI; Didn't Read)

#410

Post by apical_dendrite »

LPisGood wrote: post #56

My 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…

With one colleague, I was leaving PR comments and he would just put my feedback into the AI and paste its response. So I decided to cut out the middleman and now I just @cursor and tell it to trim unnecessarily long comments.
Post reply on HN