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

I Am Not a Reverse Centaur

blog.miguelgrinberg.com

Post reply on HN
Print view View original

191–200 of 221 posts

Re: I Am Not a Reverse Centaur

#191

Post by perching_aix »

perching_aix wrote: post #150
oytis wrote: post #39

Earlier quoted context omitted.

Who gets a sense of accoplishment from prompting an LLM? Do you get a sense of accomplishment when AI draws a picture or writes a poem for you? I guess there are some minds I'll never be able to comprehend

Do you think people in product design never feel a sense of accomplishment or something? Or for another perspective, why do you think a "sense of accomplishment" is an essential, and dominantly important thing for everyone? Maybe they feel two hot shits about such a thing. Especially when the "accomplishment" in the vast majority of cases is in the realm of "having had the patience to endure the humiliation ritual of…

[dead]

Re: I Am Not a Reverse Centaur

#192

Post by Thrymr »

emodendroket wrote: post #158

> Does open source matter anymore? I mean, did it ever? It depends what you mean. Very few open source or free software projects are successful in any meaningful sense.

Considering that the whole industry, including the big AI companies, is built on top of open source now, I would have to say it did matter. That doesn't mean every project mattered (in a larger sense), but certainly thousands of open source projects have value, and dozens have contributed enormous value. The fact that the value has been disconnected from the maintainers has been a problem for a long time, but it is getting worse, and this is one example of a maintainer near the breaking point.

Re: I Am Not a Reverse Centaur

#193

Post by mplewis »

WhitneyLand wrote: post #187

The PR quality problem is legit and needs a solution. But saying his opinion hasn’t changed on this: “the main and most important reason why GenAI tools do not work for me is that they do not make me any faster.” It’s been a year and agents and models have improved dramatically. I can see for some things it doesn’t make sense, but not using it at all because there’s nothing it can help with? Devs who don’t use models…

Why is that any of your business?

Re: I Am Not a Reverse Centaur

#194

Post by IcyWindows »

slopinthebag wrote: post #188
seanlinehan wrote: post #151

Earlier quoted context omitted.

I think that's fair for certain one-shot generations. For example, sending off a single prompt to an image or music generator and just accepting the output. But I think most of this stuff is iterative, multi-turn. You type a thing in, see what comes back, and then repeat until you have something that satisfies your desire. Taking the manager analogy. If you spent 30-minutes writing up a draft spec, waited for the out…

Taking the art commission approach, you go back and forth with the artist until you have what you want. Should you feel pride? I think it's much closer to the art commission than it is to a manager who is managing humans, the constraints of the business, customers, etc.

Maybe a movie producer is a better analogy?

Re: I Am Not a Reverse Centaur

#195

Post by eranation »

Asking contributors to first make sure there is an approved requirement before creating a PR sounds like a great idea regardless of the use of LLM.

But another issue is - AI disclosure (agent, model etc). I'm sure others tried similar approaches, but in case this is not common knowledge - I tried to see what happens if you ask agents to disclose themselves in the PR description / comments in a rule file.

It seems to work pretty well as most AI "assisted" PRs will be opened by agents using the gh cli or MCP on behalf of the user. (Of course this can be bypassed, but for someone who doesn't mind disclosing or doesn't care, this is a good step forward)

Example: https://github.com/arnica/depsguard/blob/main/AGENTS.md#ai-d...

(so far worked on PRs from both Claude Code and Codex - both got a footer disclosure of the agent name and model)

Re: I Am Not a Reverse Centaur

#196

Post by ctoth »

mostlysimilar wrote: post #33
the_af wrote: post #30

Earlier quoted context omitted.

I get where you're coming from, but for completely non-technical people, it seems to me the more precise analogy is not "building" but "ordering online". Or hiring someone to do something for you. If you order a pizza from an app, and assume you can pick ingredients from a checklist, would you consider it "making" a pizza? Would people get the feeling of accomplishment?

That's a better analogy than my dumb drawing one. You can be happy you got your pizza and you can enjoy the taste but it is not an accomplishment to be proud of.

The pizza analogy smuggles in this idea of cheep/mass-produced. I'm talking about blind people who can now prompt their way to an accessibility mod for their favorite game, the sort of thing which literally would have never been written before. How you know it wouldn't've been written is by counting the accessibility mods pre and post LLM.

Now generalize this. Every tiny community, every person with a disability, everybody for whom the default software doesn't work right? Can now change it specifically for them. Not add peperoni, that's far too low-dimensional to capture what is happening. Actually build their own interface, be able to use something they simply didn't have access to before, and critically not depend on another programmer (there are like a dozen of us blind ones!) to build something for them.

Re: I Am Not a Reverse Centaur

#197

Post by ahartmetz »

greiskul wrote: post #172
ahartmetz wrote: post #160

Earlier quoted context omitted.

If you already know it's not good enough, you can just say so by calling it a proof of concept or hack to demonstrate what needs to be done. Such code is often very useful when writing the real fix.

Yup, some of my first contributions when I was a teenager, was to an open source project where I was able to find a couple of bugs, and implement a hacky solution that I shared with the team on the forum. My code was absolutely awful, but by having done both the effort of tracking down the cause of the bug, and one possible way of fixing it (which was badly coded, but worked), made the developers able to quickly turn…

I've done the same for a fix in the Gold linker, which is now obsolete due to even faster linkers being available. Shout out to Ian Lance Taylor, his behavior as the maintainer was exemplary: very gracious and very responsive.

Re: I Am Not a Reverse Centaur

#198

Post by cgio »

toponijo wrote: post #82
aidenn0 wrote: post #60

I first encountered the following concept in one of Oxide's publications; good chance it didn't originate there though: There is an implicit social contract with writing that the writer has put more effort into writing than the reader will need to read something. Sure you get crackpots still, but there are only so many Gene Rays in this world, so the volume is limited. I think the same applies to PRs. Pre-AI , it was…

Given this, you can conclude that writers should be putting in at least at much effort as readers, whether or not they use an LLM. What really seems to be the problem is writers that don't at least check their own work, and pass that burden onto the readers. This is easier than ever with LLMs. This is toxic behavior that unfortunately rewards a selfish writer. I'm worried the AI push incentivizes this too much, to wh…

I think that this is the essence of the argument. I spent two weeks of long nights across a few different sessions with millions of tokens generated, to produce a 5 page proof. I think we have come to the age of the aesthetics of curation. At least I don’t feel like I broke this silent contract. The effort you put in driving the torrent of words before distilling it is a new art. First time I tried it and it felt more creative than slop. The judgement nevertheless lies on the eye of the beholder.

Re: I Am Not a Reverse Centaur

#199

Post by ryandrake »

ErroneousBosh wrote: post #175
gedy wrote: post #167

Earlier quoted context omitted.

Yes I basically meant those folks weren't very good developers to begin with and now extrapolating to: "wow this is better than all devs!" , when it's more like "it's you, dude"

This sounds awfully like the people who think that self-driving cars and even auto-braking systems will eliminate all accidents, because everyone else is as bad a driver as they are.

Someone pointed out[1] a while ago that LLMs look good at things you are bad at. Which is I think one of the best explanations of why so many people disagree about how good they are at programming. There are a lot of people really bad at programming, and they will look at the output if an LLM and say “Wow, it’s so much better than my code!”

1: https://news.ycombinator.com/item?id=48315309

Re: I Am Not a Reverse Centaur

#200

Post by bigstrat2003 »

slopinthebag wrote: post #123
luma wrote: post #119

Earlier quoted context omitted.

Developing a functional app that meets your needs with an LLM takes it's own kind of skill, and is substantially more difficult if you can't recognize when the machine is steering your architecture in the wrong direction. It takes actual, real work. It's certainly a completely different kind of work than writing most of the code yourself, but so is using Java when compared to hand writing x86 opcodes. Prompting an LL…

I'm not saying people can't have fun , I'm saying it's a misplaced sense of pride that gives me the ick when I sense it in others. I see plenty of people who readily disclose that their thing they "built" was just slopped together by an LLM and this is perfectly okay, because they aren't trying to take credit for accomplishments that they didn't put in the expected effort for. The difference between the skill & effor…

Yeah, there's something pathetic about being proud of something you didn't actually get challenged by making. Like, I love building Lego sets. It's relaxing, it's fun, and I enjoy having the completed model to put on a shelf and look at. But I would never in a million years say I was proud of those Lego models, or that I had a sense of accomplishment. That wouldn't be merited.
Post reply on HN