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]
Stop posting slop.
From specification to stress test: a weekend with Claude
11–20 of 35 posts
Re: From specification to stress test: a weekend with Claude
#12Over a weekend, between board games and time with my kids, Claude and I built a distributed system with Byzantine fault tolerance, strong consistency and crash recovery under arbitrary failures. I described the behaviour I wanted in Allium, worked through the bugs conversationally and didn't write a line of implementation code.
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"
Re: From specification to stress test: a weekend with Claude
#13Re: From specification to stress test: a weekend with Claude
#14> Allium has no compiler and no runtime. It is purely descriptive, defined entirely by its documentation
That seems ill advised at best.
Re: From specification to stress test: a weekend with Claude
#15Is 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.
Re: From specification to stress test: a weekend with Claude
#16As 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…
So we are now at the stage that AI coding agents don’t work because you can’t create a good google docs alternative from scratch without dependencies with $170 in one weekend.
Re: From specification to stress test: a weekend with Claude
#17Earlier quoted context omitted.
Stop posting slop.
[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 correct, but I'd at least know that someone cared enough to write it and all of it made sense from that person's perspective. Sometimes I am interested in an LLM's take on a topic, but not when browsing a forum for humans.
Re: From specification to stress test: a weekend with Claude
#18As 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…
> For anything that requires taste and judgment, we've still got a long way to go. There are lots of great demos out there but few if any real examples of vibe coded (or whatever you want to call it) software standing alone as an alternative to project people wrote
Yeah, we still have exactly the same problem as before LLMs/agents, namely that we lack people with "Good Taste". I've outlined how I feel about before (https://emsh.cat/good-taste/) but the TLDR is basically that while LLMs can help you move faster, they won't suddenly mean you'll make better choices, probably the reverse is true, you'll move faster and make worse choices.
Having good taste and knowing how things actually should function is 80% of the work of building good software, and so far all these tools that are trying to replace human choices lead to worse software, and we need more tooling that puts the human and the LLM working together, instead of just outsourcing from the human to the LLM.
Re: From specification to stress test: a weekend with Claude
#19This post appears to essentially be an ad for Allium, so I’m gonna focus on that.
I don’t fully understand how allium solves the inherent issues with markdown, i.e. free-form language specs. It appears to have some loose syntactical rules, but outside of that relies on comments which are, again, free-form. Moreso, the “Resolved” portions remind of me how LLM agents like Claude code just go and edit existing doc files and make a mess of repetitive and overlapping thoughts.
Re: From specification to stress test: a weekend with Claude
#20As 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…
So we are now at the stage that AI coding agents don’t work because you can’t create a good google docs alternative from scratch without dependencies with $170 in one weekend.
I think the conclusion is that Vibe oding is shit, and I agree with this, but having an AI assistant that can do some specific tasks that you can review is a good strategy.
I also have a story about Vibe Coding, I had the AI make for me a mqarkdown editor with some extra features, it worked fine but the problem is I have no idea how it works, I do not know if I can add feature X easily or it needs a rewrite from scratch, I have no ideas for improvements or new features, if there is a problem I have no clue what causes it since I I never looked at the code.
So I concluded that I (others can do whatever they want, they are free people with their own standards ) I will only use Vibe Coding for throw away personal shit, that I will not make public, like for example I made some bash scripts, some python scripts to automate some stuff.