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

641–650 of 729 posts

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

#641

Post by port11 »

arcanemachiner wrote: post #542
unknownfuture wrote: post #413

Earlier quoted context omitted.

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.

Or when it references "item 06" from some plan you wrote as if it had any relevance to you whatsoever.

I’ve a codebase filled with references to §x.y section of documentation that Claude itself prepares and never updates; which is exactly what many devs would do, I guess, joke’s on us.

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

#642

Post by jerezzprime »

Ampersander wrote: post #543
jerezzprime wrote: post #377

Earlier quoted context omitted.

To play devil's advocate here, it is possible for someone to simultaneously use AI to write and also not be a meat proxy. I'm not saying that is the norm, but I have written docs where the vast majority of the words come from AI, but I also spent multiple days on the substance and content.

Maybe if you only use the LLM to proof read or something? I don't know if LLMs are actually any good for this purpose, but it's something I came to think of when trying to answer your question. I do think that it is very difficult to not be a meat proxy when you utilize an LLM for writing tasks. These tools are computer programs that generate text, so what else would you do with it than have it write for you? This is…

I find that the LLM is great for helping with the starting problem. I will go for a walk and basically brain dump my thoughts and ideas about a topic/doc into a voice note, where I can ramble, wander from point to point, etc. Then I transcribe it, get a model to take that and turn it into something cohesive, and then I spend multiple hours reading it, reworking it, and editing it. I am not very good at writing docs and this method produces something with far more detail and quality than I would ever get on my own. But AI;DR right?

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

#643

Post by qarl2 »

wpietri wrote: post #634
qarl2 wrote: post #633

Earlier quoted context omitted.

Yes, I agree - no comment in these threads is for the recipient. It’s for the audience. And I appreciate you engaging with me earnestly and thoughtfully. But I disagree with your “toxic”. I think HN has a fear of conflict: the “civility” argument from politics/Clinton circa 2016. And look where we are today. Sadly, conflict is sometimes necessary to resolve problems. For example, right now, the anti-AI thing is pure…

Again, bub, I'm not uncomfortable. I am saying you are a bad HN participant, making this place worse. I am not averse to conflict, but neither am I fond of dressing up an enjoyment of conflict and pointless drama as something that's somehow healthy.

Yes, I understand what you are saying. And I’m saying I disagree.

> bub

And now I’m sorry for your anger.

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

#644

Post by a2ff6eeb0 »

NateEag wrote: post #497
a2ff6eeb0 wrote: post #467

Earlier quoted context omitted.

It's the management desired direction, if the place is anything like my workplace. Everyone is all in on AI, and if you're not using it for everything possible, you're on the chopping block. And, really, it works. You can copy and paste between tickets and Claude, and then do manual testing. Then you tell Claude to self-review for clarity and minimalism, and stop worrying. Sure, today it's not as good as a human, but…

Your boss can get Claude to make unreadable, noisy, confusing code just as well as you can. There may not be a career left in software development with these monstrosities, but if there is, it's in using decades of experience to get the abominations to produce something other than unreadable dreck. If the code itself truly doesn't matter any more, programmers will no longer be paid.

Oh, yeah, the amount of skill needed for programming is quite low these days, the people paying just haven't figured it out quite yet. There's still some needed, but it's closer to line cook than nuclear physicist.

But the managers won't do it, because you still need manual testing to make sure that the AI models got things right. Managers will want to hire someone to do the manual testing.

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

#646

Post by tehlike »

Uptrenda wrote: post #578
tehlike wrote: post #465

Earlier quoted context omitted.

This has been a thing for long while, on codex too. You ask it to do something, then tell it to do something in a different way, then it assumes it needs to do the refactor in a backward compatible way, or creates migrations for it etc.

I remember when I was updating some formats for my apps data files and it ended up writing v2 and laying it on top of the old one. Ended up just telling it to delete the entire feature and start again. I do think claude.md instructions help though.

They do. But you need to remember.

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

#647

Post by otterley »

godwinson__4-8 wrote: post #612
otterley wrote: post #447

Earlier quoted context omitted.

What I meant by "optional" work is that it's not being performed for a buyer; it's volunteer labor. Nobody's paying for individuals' awful LinkedIn posts. I suppose it could be framed as self-promotion aimed at a potential future payoff, but if it repels buyers, then it's pointless. Perhaps it's worth looking at this issue from the demand side instead. Who is the customer or buyer of the AI-generated work; and if the…

As to the first part, if you mean the demand side as in who wants to read slop LinkedIn posts, LLMs haven't changed the fundamental nature of that. It's always been awful. Therefore the point is who cares if an AI has written it. As I said, it's all pablum anyway. But I don't agree with how you are describing the problem. Most marketing or self promotion is "optional" then? Why is not having a direct buyer asking for…

> As I said earlier, if a human cares a human will author.

That is precisely the observation we're not seeing.

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

#648

Post by tcmart14 »

matheusmoreira wrote: post #472
tcmart14 wrote: post #446

Earlier quoted context omitted.

Just hit "deny." I've been training my co-workers that the AI-isms their "AI Assisted coding" do that some shit just isn't acceptable. I leave a comment and hit deny. It also helps that I control the policies on the repo and they can't merge in with a denial from anyone. So it's either a fix it, or explain why your work isn't getting done. My manager is also 100% with this. I've denied for poor branch names and commi…

... Poor branch names?

Yea, its not one I exactly agree with. But it is what the team collectively as a whole said is something is important. So to the other comments acting like I am just being ridiculous. Everything I deny PRs on is something time and time again the team collectively agrees on when asked how code should look and the process and all of that. The team can choose at any time to change that and for some reason, enough people on the team when asked in a meeting if branch names matter a lot and if they should follow a certain format, its a yes.

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

#649

Post by yuye »

mikhmha wrote: post #360

Recently I've gotten lots of DM's from boutique marketing firms offering to promote the game i'm working on. I'm pretty sure they all find leads via scraping the Steam API. Many of these small firms are people in developing countries. It's frustrating dealing with them since they all use AI in communications. Everything is written so flowery and with so much extra words. Any feedback I give is met with overwhelming p…

>But I always tell them I'd rather they write in broken English to communicate their own ideas. I want to hear what they have to say, directly from their brain. I don't have issues with parsing bad english. Usually its straight and to the point.

I work in FAANG at a non-US office, and this is what I tell my colleagues. I always get pushback: "They're too shy to speak English".

They'll often write messages in their native language, then ask AI to translate.

This is in a developed country, by the way. Engineers working for a US-based company refusing to speak English while getting paid handsomely.

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

#650

Post by godwinson__4-8 »

otterley wrote: post #647
godwinson__4-8 wrote: post #612

Earlier quoted context omitted.

As to the first part, if you mean the demand side as in who wants to read slop LinkedIn posts, LLMs haven't changed the fundamental nature of that. It's always been awful. Therefore the point is who cares if an AI has written it. As I said, it's all pablum anyway. But I don't agree with how you are describing the problem. Most marketing or self promotion is "optional" then? Why is not having a direct buyer asking for…

> As I said earlier, if a human cares a human will author. That is precisely the observation we're not seeing.

> That is precisely the observation we're not seeing.

What is the basis for this claim? To me, my formulation reads as logically self evident, to the point of near tautology. Your claim is what? People who genuinely care about things are delegating those things to LLMs? Then in what sense do they actually "care" about them?

Post reply on HN