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

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

maggieappleton.com

Post reply on HN
Print view View original

291–300 of 466 posts

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

#291

Post by directevolve »

sdwr wrote: post #265
directevolve wrote: post #225

Earlier quoted context omitted.

In what rationalist writing? The LessWrong style is to be literal and unambiguous. They’re pretty explicit that this is a community value they’re striving for.

The whole trick is having your cake and eating it too. The LessWrong style exploits the gap between the strength of the claims ("this is a big deal that explains something fundamental about the world") and the evidence/foundation (abstract armchair reasoning, unfalsifiable)

That’s not the same issue, though. You’re claiming just plain overconfidence or that you find their arguments unconvincing. But the rhetorical trick we were discussing is oscillating between treating a claim as a joke or as deadly serious depending on the audience.

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

#292

Post by sarchertech »

0xbadcafebee wrote: post #182
habinero wrote: post #140

Earlier quoted context omitted.

That's a terrible analogy lol. 1. Chefs do learn the chemistry, at least enough to know why their techniques work. 2. Food scientist is a real job 3. The supply chain absolutely does have scientists involved in day to day operations lol. A better analogy is just shoving the entire contents of the fridge into a pot, plastic containers and all, and assuming it'll be fine.

> Chefs do learn the chemistry, at least enough to know why their techniques work Cooks are idiots (most are either illegal immigrants with no formal education, or substance-abusing degenerates who failed at everything else) who repeat what they're told. They think ridiculous things, like that searing a stake "seals in the juices", or that adding oil to pasta water "prevents sticking", that alcohol completely "cooks…

Cooks also repeatedly cook the exact same recipe designed by someone else over and over again. In our industry cooks are closest to the CPU executing machine code.

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

#293

Post by ewoodrich »

esperent wrote: post #283
jsheard wrote: post #30

Earlier quoted context omitted.

Did you catch the part where it crossed over into a crypto pump-and-dump scam, with Yegge's approval? And then the guy behind the "Ralph" vibe coding thing endorsed the same scam, despite being a former crypto critic who should absolutely know better?

I mean, if I, as a crypto critic, saw an opportunity to suddenly make hundreds of thousands or millions on a fully legal but shady crypto scheme - purely by piggybacking on some other loudmouth (Yegge) - I'd be very hard pressed not to take it.

Perhaps, I can't say with 100% certainty that I wouldn't if offered 50k+ just for writing a blog post. But in doing so I would also have to accept being labeled a "crypto shill" instead of "crypto critic" for the rest of my life.

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

#294

Post by Ethee »

thorum wrote: post #203
Ethee wrote: post #174

Earlier quoted context omitted.

It's likely then that you are thinking too small. Sure for one off tasks and small implementations, a single prompt might save you 20-30 mins. But when you're building an entire library/service/software in 3 days that normally would have taken you by hand 30 days. Then the real limitation comes down to how fast you can get your design into a structured format. As this article describes.

Agree that planning time is the bottleneck, but > 3 days still seems slow! I’m saying what happens in 2028 when your entire project is 5-10 minutes of total agent runtime - time actually spent writing code and implementing your plan? Trying to parallelize 10m of work with a “town” of agents seems like unnecessary complexity.

I think that most of the anecdotal and research experiences I've seen for AI agent use so far tell us that you need at least a couple pass-throughs to converge upon a good solution, so even in your future vision where we have models 5x as good as now, I'll still need at least a few agents to ensure I arrive at a good solution. By this I specifically mean a working implementation of the design, not an incorrect assumption of the design which leads the AI off on the wrong path which I feel like is the main issue I keep hearing over and over. So coming back to your point, assuming we can have the 'perfect' design document which lays out everything, yeah we'll probably only need like 5 agents total to actually build it in a few years.

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

#295

Post by _zoltan_ »

anonymous908213 wrote: post #10
suriya-ganesh wrote: post #7

>Yegge is leaning into the true definition of vibecoding with this project: “It is 100% vibecoded. I’ve never seen the code, and I never care to.” I don't get it. Even with a very good understanding of what type of work I am doing and a prebuilt knowledge of the code, even for very well specced problem. Claude code etc. just plain fail or use sloppy code. How do these industry figures claim they see no part of a 225K…

The secret is that it doesn't work. None of these people have built real software that anyone outside their bubble uses. They are not replacing anyone, they are just off in their own corner building sand castles.

Of course it works. I haven't looked at code for my internal development in months.

I don't know why people keep repeating this but it's wrong. It works.

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

#297

Post by matkoniecz »

skybrian wrote: post #242
ludicity wrote: post #226

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…

He is still an evil scammer scamming people.

In the same way signposting and credibly warning "I murder people" does not make ok to murder people.

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

#298

Post by phaedrus »

If we had super-smart AI with low latency and fast enough speed, would the perceived need for / usefulness of running multiple agents evaporate? Sure you might want to start working on the prompt or user story for something else while the agent is working on the first thing, but - in my thought experiment here there wouldn't be a "while" because it'd already be done while you're moving your hand off the enter key.

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

#299

Post by matkoniecz »

freedomben wrote: post #209
mediaman wrote: post #46

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…

Links to Steve's writeup for Gas Town for those who don't have them yet: [Medium post]: https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16d... [HN Discussion]: https://news.ycombinator.com/item?id=46458936

And https://steve-yegge.medium.com/bags-and-the-creator-economy-... where you can read about its author scamming people

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

#300

Post by consumer451 »

jrmg wrote: post #27
suriya-ganesh wrote: post #7

>Yegge is leaning into the true definition of vibecoding with this project: “It is 100% vibecoded. I’ve never seen the code, and I never care to.” I don't get it. Even with a very good understanding of what type of work I am doing and a prebuilt knowledge of the code, even for very well specced problem. Claude code etc. just plain fail or use sloppy code. How do these industry figures claim they see no part of a 225K…

This is also my experience. Everything I’ve ever tried to vibe code has ended up with off-by-one errors, logic errors, repeated instances of incorrect assumptions etc. Sometimes they appear to work at first, but, still, they have errors like this in them that are often immediately obvious on code review and would definitely show up in anything more than very light real world use. They _can_ usually be manually tidied…

In my comment history can be found a comment much like yours.

Then Opus 4.5 was released. I had already had my CC cluade.md, and Windsurf global rules + workspace rules set up. Also, my main money making project is React/Vite/Refine.dev/antd/Supabase... known patterns.

My point is that given all that, I can now deploy amazing features that "just work," and have excellent ux in a single prompt. I still review all commits, but they are now 95% correct on front end, and ~75% correct on Postgres migrations.

Is it magic? Yes. What's worse is that I believe Dario. In a year or so, many people will just create their own Loom or Monday.com equivalent apps with a one page request. Will it be production ready? No. Will it have all the features that everyone wants? No. But it will do that they want, which is 5% of most SaaS feature sets. That will kill at least 10% of basic SaaS.

If Sonnet 3.5 (~Nov 2024) to Opus 4.5 (Nov 2025) progress is a thing, then we are slightly fucked.

"May you live in interesting times" - turns out to be a curse. I had no idea. I really thought it was a blessing all this time.

Post reply on HN