Live data from Hacker News

Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

maggieappleton.com

251–260 of 466 posts

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#251
It occurs to me that there is an extraordinary amount of BS coming from all the places these days and I wonder if this comes from people with actual real experience or just some hypothetical, high-level thinking game.

I mean, we use coding agents all the time these days (on auto pilot) and there is absolutely nothing of this sorts. Coding with AI looks a lot like coding without AI. The same old process apply.

I mean "I feel like I'm taking crazy pills".

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#252
I tried building something like this similar to many others here but now I’m convinced agents should just use GitHub issues and pull requests. You get nice CI and code reviews (AI or human) and state of the progress is not kept in code.

Basically simulate a software engineering team using GitHub but everyone is an agent. From tech lead to coders to QA testers.

https://github.com/mohsen1/claude-code-orchestrator

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#253
post #248
post #154

Earlier quoted context omitted.

All our best performing devs/engineers are using the tools the most. I think this is something a lot of people are telling themselves though, sure.

Best performing by what metric? There aren't meaningful ways to measure engineer "performance" that makes them comparable as far as I know.

Your org doesn't track engineering impact?

What about git stats?

I can tell you the guys that are consistently pushing code AND having the biggest impact are using LLM tools.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#254
post #227

Earlier quoted context omitted.

Because that code is presumably working and the vibe code is probably not?

do you have evidence that all vibe coded solutions dont work? Because thats what you're implying.

If I wanted to prove murder, not negligence.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#255
post #71
post #40

Earlier quoted context omitted.

> The secret is that it doesn't work. I have 100% vibecoded software that I now use instead of commercial implementation that cost me almost 200 usd a month (tool for radiology dictation and report generation).

Wait, so you're a radiologist and you're using software you vibecoded to generate radiology reports for real patients? Is that, like, allowed?

Of course it’s allowed. It’s just kind of text editor but with support of speech to text and structured reports (e.g. when reporting spine if I say l3 bd it automatically inserts description of bulging disc in the correct place in the report). I then copy paste it to RIS so there’s absolutely nothing wrong or illegal in that.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#256

I don't get the widespread hatred of Gas Town. If you read Steve's writeup, it's clear that this is a big fun experiment. It pushes and crosses boundaries, it is a mixture of technology and art, it is provocative. It takes stochastic neural nets and mashes them together in bizarre ways to see if anything coherent comes out the other end. And the reaction is a bunch of Very Serious Engineers who cross their arms and h…

> If you read Steve's writeup, it's clear that this is a big fun experiment: So, Steve has the big scary "YOU WILL DIE" statements in there, but he also has this: > I went ahead and built what’s next. First I predicted it, back in March, in Revenge of the Junior Developer. I predicted someone would lash the Claude Code camels together into chariots, and that is exactly what I’ve done with Gas Town. I’ve tamed them to…

These are some very tortured interpretations you're making.

- "what's next" does not mean "production quality" and is in no way mutually exclusive with "experimental". It means exactly what it says, which is that what comes next in the evolution of LLM-based coding is orchestration of numerous agents. It does not somehow mean that his orchestrator writes production-grade code and I don't really understand why one would think it does mean that.

- "productively" also does not mean "production quality". It means getting things done, not getting things done at production-grade quality. Someone can be a productive tinkerer or they can be a productive engineer on enterprise software. Just because they have the word "product" in them does not make them the same word.

- "working effectively" is a phrase taken out of the context of this extremely clear paragraph which is saying the opposite of production-grade: "Working effectively in Gas Town involves committing to vibe coding. Work becomes fluid, an uncountable substance that you sling around freely, like slopping shiny fish into wooden barrels at the docks. Most work gets done; some work gets lost."

If he wanted to say that Gas Town wrote production grade code, he would have said that somewhere in his 8000-word post. But he did not. In fact, he said the opposite, many many many many many many times.

You're taking individual words out of context, using them to build a strawman representing a promise he never came close to making, and then attacking that strawman.

What possible motivation could you have for doing this? I have no idea.

> If you say two different and contradictory things...

He did not. Nothing in the blog post explicitly says or even remotely implies that this is production quality software. In addition, the post explicitly, unambiguously, and repeatedly screams at you that this is highly experimental, unreliable, spaghetti code, meant for writing spaghetti code.

The blog post could not possibly have been more clear.

> ...because you did it to yourself.

No, you're doing this to his words.

Don't believe me? Copy-paste his post into any LLM and ask it whether the post is contradictory or whether it's ambiguous whether this is production-grade software or not. No objective reader of this would come to the conclusion that it's ambiguous or misleading.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#258

Earlier quoted context omitted.

I thought it was harmless(ish) fun, but David Gerard put out a post stating that Yegge used Gas Town to push out a crypto project that rug pulled his supporters, while he personally walked away with something between $50K to $100K from memory. I suppose that has little to do with the technical merits of the work, but it's such a bad look, and it makes everyone boosting this stuff seem exactly as dysregulated/unwise a…

That was very weird. In the post where he was arguably "shilling," he seems to have signposted pretty well that it was dumb, but he will take the money they offered: > $GAS is not equity and does not give you any ownership interest in Gas Town or my work. This post is for informational purposes only and is not a solicitation or recommendation to buy, sell, or hold any token. Crypto markets are volatile and speculativ…

I'm fairly certain those disclaimers were added after he got some pushback from the original post.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#259

I don't get the widespread hatred of Gas Town. If you read Steve's writeup, it's clear that this is a big fun experiment. It pushes and crosses boundaries, it is a mixture of technology and art, it is provocative. It takes stochastic neural nets and mashes them together in bizarre ways to see if anything coherent comes out the other end. And the reaction is a bunch of Very Serious Engineers who cross their arms and h…

This is just not true. Yegge is serious and thinks Gas Town is the next big thing.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#260

Earlier quoted context omitted.

> If you read Steve's writeup, it's clear that this is a big fun experiment: So, Steve has the big scary "YOU WILL DIE" statements in there, but he also has this: > I went ahead and built what’s next. First I predicted it, back in March, in Revenge of the Junior Developer. I predicted someone would lash the Claude Code camels together into chariots, and that is exactly what I’ve done with Gas Town. I’ve tamed them to…

I agree, I’m one of the Very Serious Engineers and I liked Steve’s post when I thought it was sort of tongue in cheek but was horrified to come to the HN comments and LinkedIn comments proclaiming Gastown as the future of engineering. There absolutely is a large contingent of engineers who believe this, and it has a real world impact on my job if my bosses think you can just throw a dozen AI agents at our product roa…

> "Gastown as the future of engineering"

Note the word "future" not "present". People are making a prediction of where things will go. I haven't seen a single person saying that Gas Town as it exists today is ready for production-grade engineering project.

Post reply on HN