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

I hate AI side projects

dylancastillo.co

Post reply on HN
Print view View original

111–120 of 129 posts

Re: I hate AI side projects

#111

Post by dang »

khalic wrote: post #94
dang wrote: post #64

Edit: for me the most practical insight to come out of these threads, so far, is that Show HNs for generated repos/sites/projects would be more interesting if submitters were required to share the prompts, and not just the generated output. For such projects, the prompts are the real source, while the GH repo or generated artifact is actually the object code, and if that's all that's shared, it's less interesting and…

> Prompts are the real source LLMs are non deterministic…

That's one of the major shifts happening with this technology, but I don't think it changes the point: the prompt is the input from which the output gets generated, and in that sense is the source—a generated repo is not.

Technically I suppose one should say that the input is the tuple of (prompt, model, X) where X is some bundle of factors that nobody understands, but that formulation doesn't help me think about how we should adapt to this moment.

Re: I hate AI side projects

#112

Post by dang »

rspoerri wrote: post #92
dang wrote: post #64

Edit: for me the most practical insight to come out of these threads, so far, is that Show HNs for generated repos/sites/projects would be more interesting if submitters were required to share the prompts, and not just the generated output. For such projects, the prompts are the real source, while the GH repo or generated artifact is actually the object code, and if that's all that's shared, it's less interesting and…

i can show you my prompt. it's a mess and only listing the major prompts. but it's interesting to look at (for me at least). archive: https://github.com/ludos1978/ludos-vscode-markdown-kanban/bl... in progress or undone: https://github.com/ludos1978/ludos-vscode-markdown-kanban/bl... and there is much improvement, because if often watch videos next to vibe coding the project and do it in minutes i have time. so histo…

Thanks—I agree that it's interesting to look at, and a submission of the project that included this would be much better than a submission of the same project that did not include it.

Re: I hate AI side projects

#113

Post by dang »

tombert wrote: post #67
dang wrote: post #64

Edit: for me the most practical insight to come out of these threads, so far, is that Show HNs for generated repos/sites/projects would be more interesting if submitters were required to share the prompts, and not just the generated output. For such projects, the prompts are the real source, while the GH repo or generated artifact is actually the object code, and if that's all that's shared, it's less interesting and…

It's not a terrible idea, but I'm not sure how that would work logistically. When I use Codex to do vibe coding stuff, I don't usually have one big prompt, I usually have it do small things piecemeal and I iterate with it later. Maybe I'm using it wrong but it tends to be more "conversational" and I think that would be harder to share, especially considering I'll do things over dozens of sessions. I suppose I could k…

I'm not sure how it would work. That would have to be figured out, so we would start with the simplest implementation that is not nothing.

The limitations you're describing seem mostly to have to do with tooling, rather than objections in principle.

Re: I hate AI side projects

#114

Post by dang »

selridge wrote: post #79
btrettel wrote: post #78

Earlier quoted context omitted.

I have a daily journal where I put every online post I make. I include anything I send to a LLM on my own time in there. (I have a separate work log on their computer, though I don't log my work prompts.) Likely I miss a few posts/prompts, but this should have the vast majority. A few caveats: I'm not a heavy LLM user (this is probably what you're getting at) and the following is a low estimate. Often, I'll save the…

No the same question CANNOT be asked of source code because it can execute. You might as well ask for a record of the conversations between two engineers while code was being written. That's what the chat is. I have a pre-pre-alpha project which already has potentially hundreds of "prompts"--really turns in continuing conversations. Some of them with 1 kind of embedded agent, some with another. Some with agents on th…

> maybe you don't have the necessary perspective to understand what you're asking for

Please don't cross into personal attack. You're making fine points, and that's enough.

https://news.ycombinator.com/newsguidelines.html

Btw, I think this is a particularly good point: "You might as well ask for a record of the conversations between two engineers while code was being written. That's what the chat is."

That's a good reframing. I can see why it might be impractical to share all of that, hard to make sense of as a reader, and too onerous to demand of submitters.

Since you have experience in this area, I'd like to hear your view on what we could reasonably require submitters to share, given that the flood of generated Github repos is creating a lot of low-quality submissions that don't gratify curiosity and thus don't fit the spirit of either Show HN or HN in general.

Some people would say "just ban them", but I'd rather find a way to adapt to this wave, since it is the largest technical development in a long time, and the price of opposing it is obsolescence.

Re: I hate AI side projects

#115

Post by dang »

selridge wrote: post #69
dang wrote: post #64

Edit: for me the most practical insight to come out of these threads, so far, is that Show HNs for generated repos/sites/projects would be more interesting if submitters were required to share the prompts, and not just the generated output. For such projects, the prompts are the real source, while the GH repo or generated artifact is actually the object code, and if that's all that's shared, it's less interesting and…

“Share the prompts” How would that be feasible for a project of any complexity whatsoever?

I don't know! We'd have to figure something out along the way.

Btw I realize "prompt" is no longer the right word for this but I don't know what a better term would be. "Conversation with LLM" is too clumsy.

Re: I hate AI side projects

#116

Post by tombert »

dang wrote: post #113
tombert wrote: post #67

Earlier quoted context omitted.

It's not a terrible idea, but I'm not sure how that would work logistically. When I use Codex to do vibe coding stuff, I don't usually have one big prompt, I usually have it do small things piecemeal and I iterate with it later. Maybe I'm using it wrong but it tends to be more "conversational" and I think that would be harder to share, especially considering I'll do things over dozens of sessions. I suppose I could k…

I'm not sure how it would work. That would have to be figured out, so we would start with the simplest implementation that is not nothing. The limitations you're describing seem mostly to have to do with tooling, rather than objections in principle.

I certainly don’t disagree with the idea; AI stuff can be so low-effort that requiring some how-to makes sense.

I am just not 100% sure how it will be implemented. Maybe even a high-level overview of roughly what the conversation looks like.

Re: I hate AI side projects

#117

Post by perrygeo »

skeledrew wrote: post #65
perrygeo wrote: post #59

Earlier quoted context omitted.

Doing things "faster" and "easier" is an interesting way to put it. It places all of the value on one's personal experience of using the AI, and completely ignores the quality of the thing produced. Which explains why most stuff produced by LLMs is throwaway garbage! It only reinforces the parent comment - there is virtually no emphasis on making things "better".

There won't even be a quality conversation if a thing isn't built in the first place, which is the tendency when the going is slow and hard. AI makes the highly improbable very probable.

I agree. I think this is the LLM superpower: making quick prototypes that allow us to speak concretely about technical tradeoffs.

My comment was pointed at people who use AI specifically with the goal of making anything easier and faster. Doesn't matter what it is. "Faster and easier is better". as though doing more of the same shit are primary goals in themselves.

If you're using AI to explore better technical decisions, you're doing it right! AI can be a catalyst for engineering and science. But not if we treat it like a mere productivity tool. The quality of the thing enabled by the AI very much matters.

Re: I hate AI side projects

#118

Post by acheron »

sodapopcan wrote: post #37
acheron wrote: post #29

Earlier quoted context omitted.

“I hate stuff” articles considered harmful.

The internet is only for training data and praising any and all technological progress. If you don't like it, keep it to yourself. Self-expression has no place here!

Ok. In this case I was making a joke combining the earlier comments in the thread about articles titled “I hate [x]” with the time-honored article title “[x] considered harmful”. Whether that’s useful for training data, only our AI overlords can tell.

Re: I hate AI side projects

#119

Post by selridge »

dang wrote: post #114
selridge wrote: post #79

Earlier quoted context omitted.

No the same question CANNOT be asked of source code because it can execute. You might as well ask for a record of the conversations between two engineers while code was being written. That's what the chat is. I have a pre-pre-alpha project which already has potentially hundreds of "prompts"--really turns in continuing conversations. Some of them with 1 kind of embedded agent, some with another. Some with agents on th…

> maybe you don't have the necessary perspective to understand what you're asking for Please don't cross into personal attack. You're making fine points, and that's enough. https://news.ycombinator.com/newsguidelines.html Btw, I think this is a particularly good point: "You might as well ask for a record of the conversations between two engineers while code was being written. That's what the chat is." That's a good r…

"maybe you don't have the necessary perspective to understand what you're asking for"

this is in no way a personal attack. It's just a statement that's true. I didn't imply anything about them or their character or limitations, but they might not have the necessary perspective if that's the question they are asking.

I think it's critically important people figure out what they want to learn from what's being shared.

What do you need from submitters here? Even setting aside the burden of supplying it, what do you hope to learn?

Re: I hate AI side projects

#120

Post by selridge »

dang wrote: post #115
selridge wrote: post #69

Earlier quoted context omitted.

“Share the prompts” How would that be feasible for a project of any complexity whatsoever?

I don't know! We'd have to figure something out along the way. Btw I realize "prompt" is no longer the right word for this but I don't know what a better term would be. "Conversation with LLM" is too clumsy.

I really have no idea. There's almost no good mapping from conversation to code. Take e.g. https://github.com/Protonk/PAWL

There's...thousands of conversations in dozens of different configurations over months to make that. What...out of that do you want to know? What do you deserve to know by dint of my making a submission?

Those aren't rhetorical. I think if you can answer those two, that's a fair start. Good luck lol.

Post reply on HN