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

From specification to stress test: a weekend with Claude

juxt.pro

Post reply on HN
Print view View original

21–30 of 35 posts

Re: From specification to stress test: a weekend with Claude

#21

Post by mr_mitm »

amarble wrote: post #5

As a counterpoint, I also tried writing something with Claude last weekend: a Google docs clone[1]. I spent $170 on Anthropic API credits, and got something that did mostly what I asked but was basically useless. It seems that for simple interfaces for which there is an exact specification, like the recent compiler and web browser examples, it's possible to write bigger projects that "work" as a demo although not in…

Does "vibe coding" now mean the agent needs to produce a working product in one shot? Or not even just working, but meeting unspecified requirements? I thought in the original phrasing by Karpathy it meant that you don't care about the code, yet you may still iterate because you might care about the product. I tried out the "Impeccable" skill for Claude Code and found it to be very useful if you care about visual aspects and good UI/UX. (I vibe coded a web app for tracking personal finances where I used this skill, see: https://github.com/AdrianVollmer/Solvency. Not one-shotted, and not perfect, but personally I'm impressed with what is possible in a few weekends with a $90 subscription to Claude.)

Re: From specification to stress test: a weekend with Claude

#22

Post by SPICLK2 »

retsibsi wrote: post #12
SPICLK2 wrote: post #4

Earlier quoted context omitted.

I don't see why you need to bring your kids into this, and as a parent any suggestion of being distracted by tech during time with the kids raises my suspicions. We have a strict no laptops and no phones rule when the kids are around (unless we're specifically doing something with them using those tools - looking at the weather forecast, or looking up some information). "I can prompt AI while playing with the kids" i…

They said "between", not "during"; I think the point was that they didn't spend a full weekend with Claude. edit: anyone care to explain why this is a bad comment, rather than just downvoting? The GP comment says "Over a weekend, between board games and time with my kids,", and the parent comment lectures them based on an obvious strawman: "I can prompt AI while playing with the kids"

I'll bite.

"between time with the kids" is another person's "during time with the kids".

For me, "between time with the kids" means my kids are engaged in another activity that does not require my input until they are done with it. Whatever I am doing during this time also is typically very interruptible, so I am ready to help the kids along to their next "thing" (the joys of being a parent!). On a typical weekend (my oldest is 7), I'll get maybe 2 hours of this time during the time my kids are awake.

Re: From specification to stress test: a weekend with Claude

#23

Post by asksomeoneelse »

boxed wrote: post #15
asksomeoneelse wrote: post #8

Is there a link to the specification and the resulting generated code ? I skimmed through the article and the author's github profile, but couldn't find anything related. Seems like a serious oversight if this is your selling point.

Their docs say: > Allium has no compiler and no runtime. It is purely descriptive, defined entirely by its documentation From what I understand that means there is no spec, no parser, it's just vibe evaluated by LLMs.

Sorry, I meant the spec and code of the toy project described in the post.

I don't necessarily expect their secret sauce to be openly available. But given the grandiose claims made there, I do expect something to back it up other than a corpospeak "trust me bro".

Re: From specification to stress test: a weekend with Claude

#24

Post by retsibsi »

SPICLK2 wrote: post #22
retsibsi wrote: post #12

Earlier quoted context omitted.

They said "between", not "during"; I think the point was that they didn't spend a full weekend with Claude. edit: anyone care to explain why this is a bad comment, rather than just downvoting? The GP comment says "Over a weekend, between board games and time with my kids,", and the parent comment lectures them based on an obvious strawman: "I can prompt AI while playing with the kids"

I'll bite. "between time with the kids" is another person's "during time with the kids". For me, "between time with the kids" means my kids are engaged in another activity that does not require my input until they are done with it. Whatever I am doing during this time also is typically very interruptible, so I am ready to help the kids along to their next "thing" (the joys of being a parent!). On a typical weekend (m…

That all makes sense, but I don't see how it supports your uncharitable read of the original comment. Both because they could very easily have meant something a bit different (we have no idea how old the kids are or whether they were even around all weekend; maybe there were times when they were at friends' houses or similar), and because vibe coding could be the interruptible activity they do while the kids are busy. Maybe you feel strongly that it's not a legitimate use of that kind of semi-downtime, but we don't know if that's what they were talking about in the first place.

Re: From specification to stress test: a weekend with Claude

#25

Post by SPICLK2 »

retsibsi wrote: post #24
SPICLK2 wrote: post #22

Earlier quoted context omitted.

I'll bite. "between time with the kids" is another person's "during time with the kids". For me, "between time with the kids" means my kids are engaged in another activity that does not require my input until they are done with it. Whatever I am doing during this time also is typically very interruptible, so I am ready to help the kids along to their next "thing" (the joys of being a parent!). On a typical weekend (m…

That all makes sense, but I don't see how it supports your uncharitable read of the original comment. Both because they could very easily have meant something a bit different (we have no idea how old the kids are or whether they were even around all weekend; maybe there were times when they were at friends' houses or similar), and because vibe coding could be the interruptible activity they do while the kids are busy…

"Hours spent on the project" would be a much more useful metric, with no confounding variables. As it is, the mere mention of interleaving time with your kids and time engrossed in tech hits a nerve at time when IMO too many parents are doing this already, and lends unwarranted validity to the idea.

Re: From specification to stress test: a weekend with Claude

#26

Post by altmanaltman »

retsibsi wrote: post #17
altmanaltman wrote: post #13

Earlier quoted context omitted.

[flagged]

I don't think people should be rude to you, but the comment was AI-generated, right? Lots of people dislike that as it feels kind of wasteful and disrespectful of our time; it can literally take you less time to generate the comment than for us to read it, and the only information you added is whatever was in the (presumably much shorter) prompt. If you'd written it yourself, it may or may not be interesting and corr…

I'm sorry but if you're blaming some text on a website to be "disrespectful of our time", I don't know what to say to you.

I stand behind everything on my comment and I have engaged in good faith with every single reply to it here (even though none of them talk about anything in the comment itself).

Go through my profile, see how I engage with people and tell me again I'm AI.

If you do not have anything to say to the subject matter of a comment and just have personal snide remarks, I do think it's a waste of your time but do not blame me for it or tell me to leave the platform.

Typing this comment right now is a waste of time for me but I do not feel the need to grandstand over it as if there's a massive opportunity cost to it. I'm a human writing/interacting in a "forum for humans."

Re: From specification to stress test: a weekend with Claude

#27

Post by retsibsi »

altmanaltman wrote: post #26
retsibsi wrote: post #17

Earlier quoted context omitted.

I don't think people should be rude to you, but the comment was AI-generated, right? Lots of people dislike that as it feels kind of wasteful and disrespectful of our time; it can literally take you less time to generate the comment than for us to read it, and the only information you added is whatever was in the (presumably much shorter) prompt. If you'd written it yourself, it may or may not be interesting and corr…

I'm sorry but if you're blaming some text on a website to be "disrespectful of our time", I don't know what to say to you. I stand behind everything on my comment and I have engaged in good faith with every single reply to it here (even though none of them talk about anything in the comment itself). Go through my profile, see how I engage with people and tell me again I'm AI. If you do not have anything to say to the…

I didn't say or think that your account was AI-run, and I didn't tell you to leave the platform. I just tried to explain why your comment might have annoyed people and triggered negative responses (while agreeing that the rude ones were inappropriate).

Re: From specification to stress test: a weekend with Claude

#28

Post by altmanaltman »

retsibsi wrote: post #27
altmanaltman wrote: post #26

Earlier quoted context omitted.

I'm sorry but if you're blaming some text on a website to be "disrespectful of our time", I don't know what to say to you. I stand behind everything on my comment and I have engaged in good faith with every single reply to it here (even though none of them talk about anything in the comment itself). Go through my profile, see how I engage with people and tell me again I'm AI. If you do not have anything to say to the…

I didn't say or think that your account was AI-run, and I didn't tell you to leave the platform. I just tried to explain why your comment might have annoyed people and triggered negative responses (while agreeing that the rude ones were inappropriate).

Sure, cheers then. I don't care about negative responses if they're negative just because they think it's AI-generated, without having to say anything substantial on the actual comment or the article. I have demonstrated my willingness to engage in good faith but those comments have not.

If negative responses have no substance behind it, it makes no sense to care about them or take them seriously.

Also, the fact that you assume it takes more time reading that comment than it took for me to write is pretty weird (I still don't get what was so wrong about the comment that simply reading it is a waste of time to people).

Re: From specification to stress test: a weekend with Claude

#29

Post by antonly »

altmanaltman wrote: post #9
antonly wrote: post #6

Earlier quoted context omitted.

Hello, could you please put your over-sensationalized, overly-long, AI-generated comments somewhere else? Thank you. Kindly, the HN Community.

[flagged]

I find it interesting that you request me to discuss subject matter when your post is intellectually equivalent to: "I generated this sequence of numbers using my pseudo-random number generator"

Re: From specification to stress test: a weekend with Claude

#30

Post by retsibsi »

altmanaltman wrote: post #28
retsibsi wrote: post #27

Earlier quoted context omitted.

I didn't say or think that your account was AI-run, and I didn't tell you to leave the platform. I just tried to explain why your comment might have annoyed people and triggered negative responses (while agreeing that the rude ones were inappropriate).

Sure, cheers then. I don't care about negative responses if they're negative just because they think it's AI-generated, without having to say anything substantial on the actual comment or the article. I have demonstrated my willingness to engage in good faith but those comments have not. If negative responses have no substance behind it, it makes no sense to care about them or take them seriously. Also, the fact that…

> the fact that you assume it takes more time reading that comment than it took for me to write is pretty weird

I didn't do that either! I had no idea whether you just fired off a quick prompt and pasted the result without even reading it, or spent ages crafting and rereading and revising it, or (most likely) something in between those extremes. I said generated comments can take less time to create than to read, and that's one reason people push back against them. There's a risk that the forum just gets buried in comments that take near-zero effort to 'write' but create non-trivial time/effort/annoyance for those of us wading through them in search of actual human perspectives. And even the relatively good ones will be little different from what we could all obtain from an LLM if we wanted it.

FWIW, I didn't even get to the substance, because I instinctively bounce off LLM-written content posted in human contexts without explanation. You're obviously free not to care about that, and I wouldn't have replied and got into this meta discussion if not for the back-and-forth you were already involved in.

edit: but if you do care about getting through to people like me, even a short manually-written introduction can make me significantly more likely to read the rest of the content. To me, pure LLM output is a pretty strong signal of a bot/low-effort human account. But if someone acknowledges that they're pasting in an AI response and bothers to explain why they think it's interesting and worthwhile, I'll look at it with more of an open mind.

Post reply on HN