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

191–200 of 466 posts

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

#191

Post by enraged_camel »

ryandrake wrote: post #59
anonymous908213 wrote: post #10

Earlier quoted context omitted.

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.

Just because they're one-off tools that only one person uses doesn't mean it's not "real software". I'm actually pretty excited about the fact that it's now feasible for me to replace all my BloatedShittyCommercialApps that I only use 5% of with vibe-coded bespoke tools that only do the important 5%, just for me to use. If that makes it a "sand castle" to you, fine, but this is real software and I'm seeing real benef…

The whole "real software" thing is a type of elitism that has existed in our field for a long time, and AI is the new battleground on which it is wielded.

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

#192

Post by joshstrange »

kaydub wrote: post #189
joshstrange wrote: post #178

Earlier quoted context omitted.

Hmm, my last experience was within the last 2 months but I'm trying not to write it off as "this sucked and will always suck", that's the #1 reason I keep testing and playing with these things, the capabilities are increasing quickly and what did/didn't work last week (especially "last model") might work this week. I'll keep testing it but that just hasn't been my experience, I sincerely hope that changes because an…

I haven't seen your issue, but git is actually one of the things I don't have the llm do. When I work on issues I create a new branch off of master, let the llm go to town on it, then I manually commit and push to remote for an MR/PR. If there are any errors on the commit hooks I just feed the errors back into the agent.

Interesting, ok, I might try that on my next attempt. I was trying to have it commit so that I could use pre-commit hooks to enforce things I want (test, lint, prettier, etc) but maybe instead I should handle that myself and make it more explicit in my prompts/CLAUDE.md to test/lint/etc. In reality I should just create a `/prep` command or similar that asks it to do all of that so that once it thinks it's done, I can quickly type that and have it get everything passing/fixed and then give a final report on what it did.

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

#193

Post by FuckButtons »

CuriouslyC wrote: post #116
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…

I like gastown's moxie, it's fun, and seems kind of tongue in cheek. What I don't like is people me-tooing gastown as some breakthrough in orchestration. I also don't like how people are doing the same thing for ralph. In truth, what I hate is people dogpiling thoughtlessly on things, and only caring about what social media has told them to care about. This tendency makes me get warm tingles at the thought of the end…

I mean, isn’t the whole point of Ralph that it’s an allusion to “I’m in danger” because Claude in a for loop can do your job?

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

#194

Post by joshstrange »

enraged_camel wrote: post #187
joshstrange wrote: post #161

Earlier quoted context omitted.

I'm not trying to be rude here at all but are you manually verifying any of that? When I've had LLMs write unit tests they are quick to write pointless unit tests that seem impressive "2123/2123 tests passed!" but in reality it's testing mostly nothing of value. And that's when they aren't bypassing commit checks or just commenting out tests or saying "I fixed it all" while multiple tests are broken. Maybe I need a s…

>> When I've had LLMs write unit tests they are quick to write pointless unit tests that seem impressive "2123/2123 tests passed!" but in reality it's testing mostly nothing of value. This has not happened to me since Sonnet 4.5. Opus 4.5 is especially robust when it comes to writing tests. I use it daily in multiple projects and verify the test code.

I thought I did use Opus 4.5 when I tested this last time but I might have still been on the $20 plan and I cannot remember if you get any Opus 4.5 on that in Claude Code (I thought you did with really low limits?), so maybe I wasn't using Opus 4.5, I will need to try again.

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

#195

Post by enraged_camel »

kaydub wrote: post #157
habinero wrote: post #134

Earlier quoted context omitted.

It lets 0.05X developers be 0.2X developers and 1X developers be 0.9-1.1X developers. The problem is some 0.05X developers thought they were 0.5X and now they think they're 2X.

Nah, our best devs/engineers use the tools the most. In my real life experience it's been the middling devs that always talk about "ai slop" and how the tools can't do their jobs.

On our team there's a very clear distinction between three groups:

- those who have embraced AI and learned to use it well

- those who have embraced AI but treat it as a silver bullet

- those who reject AI

First group is by far the most productive and adds the most value to the team.

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

#196

Post by nicoburns »

ryandrake wrote: post #59
anonymous908213 wrote: post #10

Earlier quoted context omitted.

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.

Just because they're one-off tools that only one person uses doesn't mean it's not "real software". I'm actually pretty excited about the fact that it's now feasible for me to replace all my BloatedShittyCommercialApps that I only use 5% of with vibe-coded bespoke tools that only do the important 5%, just for me to use. If that makes it a "sand castle" to you, fine, but this is real software and I'm seeing real benef…

> I'm actually pretty excited about the fact that it's now feasible for me to replace all my BloatedShittyCommercialApps that I only use 5% of with vibe-coded bespoke tools that only do the important 5%, just for me to use.

Aren't you worried that they'll work fine for 3 weeks then delete all your data when you hold them slightly different? Vibe coded software seems to have a similar problem to "Undefined Behaviour", in that just because it works sometimes doesn't mean that it will always work. And there's no limit on what it might do when it doesn't work (the proverbial "nasal demons") - it might well wipe your entire harddrive, not just corrupt it's own data.

You can of course mitigate this by manually reviewing the software, but then you lose at least some of the productivity benefit.

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

#197

Post by gozzoo »

GoatInGrey wrote: post #127
hyperpape wrote: post #97

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…

Keep in mind that Steve has LLMs write his posts on that blog. Things said there may not reflect his actual thoughts on the subject(s) at hand.

There is no way for this to be true. I read his book about vibe coding and it is obvoius that it has significant LLM contribution. His blog posts though are funy and controversial, and have bad jokes, and he jumps from topic to topic. Ha has had this style like 10+ years before LLMs came around.

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

#198

Post by lovich »

ewoodrich wrote: post #179
SomaticPirate wrote: post #106

Earlier quoted context omitted.

It isn't though. It crossed the chasm when Steve (who I would like to think is somewhat comfortable after writing a book, holding a director level position at several startups) decided to endorse an outright crypto pump and dump. When he decided to monetize the eyeballs on the project instead of anything related to the engineering. Which, of course, Steve isn't smart enough to understand (in his own words) and he rec…

Okay yeah, not great... https://steve-yegge.medium.com/bags-and-the-creator-economy-...

My favorite part about that is gas town is supposedly so productive that this guys sleep patterns are affected by how much work he’s doing, but he took the time to physically go to a bank to get a 5 figure payout.

It makes it difficult to believe that gas town is actually producing anything of value.

I also lol at his bitching about how the bank didn’t let him do the transactions instantly as he describes himself how much of a scam this seems and how the worst thing is his bank account being drained, like banks don’t have a self interest in protecting their clientele from such scams.

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

#199

Post by rexpop »

martin-t wrote: post #173

Anybody here read Coding machines? There's this implied trust we all have in the AI companies that the models are either not sufficiently powerful to form a working takeover plan or that they're sufficiently aligned to not try. And maybe they genuinely try but my experience is that in the real world, nothing is certain. If it's not impossible, it will happen given enough time. If the safety margin for preventing take…

> If it's not impossible, it will happen given enough time.

I hope you might be somewhat relieved to consider that this is not so in an absolute sense. There are plenty of technological might-have-beens that didn't happen, and still haven't, and probably will never—due to various economic and social dynamics.

The counterfactual—all that's possible happens—ie almost tautological.

We should try and look at these mechanisms from an economic standpoint, and ask "do they really have the information-processing density to take significant long-term independent action?"

Of course, "significant" is my weasel word.

> we're giving the models so much unsupervised compute...

Didn't you read the article? It's wasted! It's kipple!

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

#200

Post by alecbz »

dullcrisp wrote: post #180
mbesto wrote: post #114

Earlier quoted context omitted.

Not saying it's right, but boy do I have stories about the code used in healthcare applications. Not sure how "vibecoded" programming lines of code is any worse.

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

Honestly even if this wasn't vibe-coded I'm still a bit surprised at individual radiologists being able to bring their own software to work, for things that can have such a high effect on patient outcomes.
Post reply on HN