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

Gas Town Decoded

alilleybrinker.com

Post reply on HN
Print view View original

191–200 of 245 posts

Re: Gas Town Decoded

#191

Post by hakunin »

krupan wrote: post #185

Gas town and the like all basically sound to me like, "AI is amazing! Ok, actually it isn't very good, but maybe we can just use more AI with our AI and then it'll be good!" And I'm not surprised at all to learn that this path took us to a "Maintenance Manager Checker Agent." I wonder what he'll call the inevitable Maintenance Manager Checker Agent Checker Agent? Maybe I've been in this game too long, but I've encoun…

This is a good point, but with ai it’s a little different, because both your process and ai are getting better. You build processes that can aspirationally support inferior AIs, while at the same time AIs themselves improve and meet you half way. This thought does not help my mental well being unfortunately.

Re: Gas Town Decoded

#192

Post by vessenes »

brushfoot wrote: post #160
vessenes wrote: post #156

Earlier quoted context omitted.

It is worth an install; it works very differently than an agent in a single loop. Beads formalizes building a DAG for a given workload. This has a bunch of implications, but one is that you can specify larger workloads and the agents won’t get stuck or confused. At some level gas town is a bunch of scaffolding around the benefits of beads; an orchestrator that is native to dealing with beads opens up many more benefi…

> Beads formalizes building a DAG for a given workload > gas town is [...] an orchestrator that is native to dealing with beads Thanks - this is very helpful in deciding when and where to use them. Steve's descriptions sounded to me like more RAM and Copilot Agents: > [Beads:] A memory upgrade for your coding agent > [Gas Town:] a new take on the IDE for 2026. Gas Town helps you with the tedium of running lots of Cla…

Yes he is on an extended manic episode right now - we can only sit back and enjoy the fruits of his extreme labor. I expect the dust will settle at some point, and I think he’s right that he’s on to some quality architecture.

Re: Gas Town Decoded

#193

Post by disgruntledphd2 »

krupan wrote: post #190
jaapz wrote: post #188

Earlier quoted context omitted.

I think in the end people will realise AI is not a silver bullet that will solve all problems and make all software engineers obsolete. Instead it will just become an extra tool in our toolbelt right alongside LSP, linters/fixers, unit test frameworks, well though out text editors and IDE's, etc. When the bubble has burst in a few years, the managers will have moved on to the next fad.

Yes, if it even becomes as useful as a good linter or LSP. It actually has very little I'm common with those, but maybe it could be as useful.

It's definitely helpful for search and summarisation.

In terms of prototyping, I can see the benefits but they're negated by the absurd amount of work it takes to get the code into more maintainable form.

I guess you can just do really heavy review throughout, but then you lose a lot of the speed gains.

That being said, putting a textual interface over everything is super cool, and will definitely have large downstream impacts, but probably not enough to justify all the spending.

Re: Gas Town Decoded

#194

Post by colin_jack »

krupan wrote: post #189
colin_jack wrote: post #187

Earlier quoted context omitted.

This might be worth a read, just as its from a trusted source and is more grounded: https://antirez.com/news/158

Still the same. "Hey look, I got these crappy developers (LLMs) to actually produce working code! This is a game-changer!" When the working code is a very small, limited thing.

I don't know, your talking about an incredibly talented engineer saying:

"In the past week, just prompting, and inspecting the code to provide guidance from time to time, in a few hours I did the following four tasks, in hours instead of weeks"

Its up to you to decide how to behave, but I can't see any reasons to completely dismiss this. It ends with good guidance what to do if you can't replicate though.

Re: Gas Town Decoded

#195

Post by mjr00 »

krupan wrote: post #185

Gas town and the like all basically sound to me like, "AI is amazing! Ok, actually it isn't very good, but maybe we can just use more AI with our AI and then it'll be good!" And I'm not surprised at all to learn that this path took us to a "Maintenance Manager Checker Agent." I wonder what he'll call the inevitable Maintenance Manager Checker Agent Checker Agent? Maybe I've been in this game too long, but I've encoun…

It's the Jarvis Effect.

For years we had people trying to make voice agents, like Iron Man's Jarvis, a thing. You had people super bought into the idea that if you could talk to your computer and say "Jarvis, book me a flight from New York to Hawaii" and it would just do it just like the movies, that was the future, that was sci-fi, it was awesome.

But it turns out that voice sucks as a user interface. The only time people use voice controls is when they can't use other controls, i.e. while driving. Nobody is voluntarily booking a flight with their Alexa. There's a reason every society on the planet shifted from primarily phone calls to texting once the technology was available!

It's similar with vibe coding. People like Yegge are extremely bought into the idea of being a hyperpowered coder, sitting in a dimly lit basement in front of 8 computer screens, commanding an army of agents with English, sipping coffee between barking out orders. "Agent 1, refactor that method to be more efficient. Agent 5, tighten up the graphics on level 3!"

Whether or not it's effective or better than regular software development is secondary, if it's a concern at all. The purpose is the process. It's the future. It's sci-fi. It's awesome.

AI is an incredible tool and we're still discovering the right way to use it, but boy, "Gas Town" is not it.

Re: Gas Town Decoded

#196

Post by ryanjshaw »

krupan wrote: post #189
colin_jack wrote: post #187

Earlier quoted context omitted.

This might be worth a read, just as its from a trusted source and is more grounded: https://antirez.com/news/158

Still the same. "Hey look, I got these crappy developers (LLMs) to actually produce working code! This is a game-changer!" When the working code is a very small, limited thing.

What evidence will convince you?

Re: Gas Town Decoded

#197

Post by alecco »

colin_jack wrote: post #183
alecco wrote: post #174

Earlier quoted context omitted.

That doesn't make any sense. Yegge named it Gas Town as in "refinery" because the main job for the human at this stage is reviewing the generated code and merging. " The whole point of the project is to be in control. Yegge even says the programmers who can read/review a lot of code fast are the new 10x (paraphrasing).

"I’ve never seen the code, and I never care to, which might give you pause" https://steve-yegge.medium.com/welcome-to-gas-town-4f25ee16d...

Oof, he changed that. I stand corrected.

Re: Gas Town Decoded

#198

Post by spmurrayzzz »

dchuk wrote: post #98

I’m very bought in to the idea that raw coding is now a solved problem with the current models and agentic harnesses. Let alone what’s coming in the near term. That being said, I think we’re in a weird phase right now where people’s obvious mental health issues are appearing as “hyper productivity” due to the use of these tools to absolutely spam out code that isn’t necessarily broadly coherent but is locally impress…

This has also been an interesting social experiment in that we get to see what work people think is actually impressive vs trivial.

Folks who have spent years effectively snapping together other people’s APIs like LEGOs (and being well-compensated for it) are understandably blown away by the current state of AI. Compare that to someone writing embedded firmware for device microcontrollers, who would understandably be underwhelmed by the same.

The gap in reactions says more about the nature of the work than it does about the tools themselves.

Re: Gas Town Decoded

#199

Post by PKop »

mccoyb wrote: post #29
mccoyb wrote: post #21

I think Yegge and Huntley are smart guys. I don't think they're doing a good job incubating their ideas into being precise and clearly useful -- there is something to be said about being careful and methodical before showing your cards. The message they are spreading feels inevitable, but the things they are showing now are ... for lack of better words, not clear or sharp. In a recent video at AI Engineer, Yegge comm…

Here's a separate, optimistic comment about Yegge and Huntley: they are obviously on the right track. In a recent video about Loom (Huntley's orchestration tool), Huntley comments: "I've got a single goal and that is autonomous evolutionary software and figuring out what's needed to be there." which is extremely interesting and sounds like great fun. When you take these ideas seriously, if the agents get better (by h…

> they are obviously on the right track

How can you just assert that? It's fine to say it looks like the right track to you. But in what way is it obvious?

Post reply on HN