Comments
I put in 15 hours or so with gas town this weekend, from just around the 0.1 release.
Think of as an extended bipolar-optimism-fueled glimpse into the future. Steve's MO is laid out in the medium post - but basically, it's okay to lose things, rewrite whole subsystems, whatever, this is the future. It's really fun and interesting to watch the speed of development.
I've made a few multi agent coding setups in the last year, and I think gas town has the team side about right: big boss (mayor), operations boss (deacon), relatively linear keeper of truth (witness), single point for merges (refiner), lots of coders with their code held lightly.
I love the idea of formulas - a lot of what makes gas town work and informs how well it ultimately will work is the formulas. They're close conceptually to skills.
I don't love the mad max branding, but meh, whatever, it's fun, and a perk of the brave new world where you can make stuff like for a few hundred bucks a month sent to anthropic - software can have personality again, yay.
Conceptually I think there is a product team element to this still missing - deploy engineers, product managers, visual testing. Everything is sort of out there, janky in parts, but workable to glue together right now, and will only improve. That said, the mad max town analogy is going to get overstretched at some point; we already have pretty good names for all the parts that are needed, and as coordination improves, we're going to want to add more stuff into the coordination. So, I'd like to see a version of this with normal names and expanded.
Upshot - worth a look - if beads is any indication, give it a month or two or four to settle down unless you like living on the bleeding bleeding edge.
By andrewl-hn 2026-01-069:57 As someone who never saw Mad Max, Slow Horses, Cat’s Cradle, Breaking Bad and only saw Waterworld when I was a kid all the references in this post went completely over my head, and I just think of words used in there as their own terminology. Like, if non-engineers read about chemical production.
The article was pretty Ok. Kubernetes has it's own share of obnoxious terminology that often comes up as "we name it different so that it doesn't sound like AWS". At some point you just accept the terminology in relation to the tool you use and move on.
By boredtofears 2026-01-064:441 reply Did you get anything workable out of it? How much money did you end up burning? (If you don't mind me asking)
By vessenes 2026-01-065:19 Yes, definitely. I spent about half that time poking around, understanding the setup, doing some bug fixing and put in a PR for gas town itself, although I used Claude Code separately for making the PR.
I pointed it at a Postgres time series project I was working on, and it deployed a much better UI and (with some nudging) fixed docker errors on a remote server, which involved logging in to the server to check logs. It probably opened and fixed 50 or so beads in total.
I'd reach for it first to do something complicated ("convoy" or epic) over Claude Code even as is -- like, e.g. "copy this data ingestion we do for site x, and implement it for sites y,z,,a,b,c,d. start with a formal architecture that respects our current one and remains extensible for all these sites" is something I think it would do a fair job at.
As to cost - I did not run out of my claude pro max subscription poking around with it. It infers ... a lot ... though. I pulled together a PR that would let you point some or all of the agent types at local or other endpoints, but it's a little early, I think for the codebase. I'd definitely reach for some cheaper and/or faster inference for some of the use cases.
By RugnirViking 2026-01-070:39 How do you do the multi agent setups in containers? I keep trying to figure out ways to start with stuff like this but it always boils down to I don't want to give entirely autonomous agents access to my entire filesystem and/or github perms. I just want them to be able to hack away in their own container and produce a pr I can read or test. I think something like a local git with the remote in the container pointing at the version on the machine could be a start but setting all that up is not trivial. As far as I can tell Steve is just running everything on the base machine in multiple worktreees/multiple clones of the project - which seems to put enormous amounts of trust on agents to actually create branches in a disciplined way. I can't imagine they can be trusted to?
By swiftcoder 2026-01-069:3610 reply Every time I read one of these, I'm increasingly convinced that the whole AI crowd are just high as kites 24/7. Must be some good drugs in the valley
Gergely Orosz (The Pragmatic Engineer) interviewed Yegge [1] and Kent Beck [2], both experienced engineers before vibe coding, and they express similar sentiments about how LLMs reinvigorated their enjoyment of programming. This introduction to Gas Town is very clear on its intended audience with plenty of warnings against overly eager adoption. I agree that using tools like this haphazardly could lead to disaster, but I would not dismiss the possibility that they could be used productively.
By bitexploder 2026-01-0714:42 Anecdote, but some of the time when I am blasted after a day of thinking for my job all day a design session randomly throwing shit at an LLM hits the spot. I usually make some meaningful progress on a pet project. I rarely let the LLM do much pure vibe coding. I iterate with several LLMs until it looks and feels right and then hack on it myself or let the LLM do drudgery like refactoring or boilerplate to get me over the humps. In that sense I do strongly agree.
Beck was in Melbourne a few weeks ago, and his take on LLM usage was so far divorced from what Yegge is doing that their views on what LLMs are capable of in early 2026 are irreconcilable.
By kaycey2022 2026-01-0815:241 reply What does Beck think?
By ludicity 2026-01-0923:26 He was the keynote at YOW! so I can't capture all the nuance and hope I'm not doing him a disservice with my interpretation, but the tl;dr is he:
"LLMs drastically decrease the cost of experimenting during the very earliest phases of a project, like when you're trying to figure out if the thing is even worth building or a specific approach might yield improvements, but loses efficacy once you're past those stages. You can keep using LLMs sustainably with a very tight loop of telling it to do the thing the cleaning up the results immediately, via human judgement."
I.e, I don't think he can relate at all to the experience of letting them run wild and getting a good result.
By andrepd 2026-01-0611:51 They are high on ego and self-importance, that they are.
By viraptor 2026-01-0613:12 > the whole AI crowd
It's far from a homogenous crowd. Yegge stands out with extreme opinions even from people who adopted the new tools daily.
By PunchyHamster 2026-01-0619:39 I just tune out and wonder why someone thought it's good idea to link it and expose others to the suffering
By neomantra 2026-01-0615:39 It's techno-freemasonry. One must break through the symbolism. The author wielding it and transmitting it cannot just plainly say the knowledge. We don't have the vocabulary or grammar for these new things, so storytelling and story universes convey it. The zoomorphism and cinematic references ground us in what all these bots are doing mimetically.
I'm excited the author shared and so exuberantly; that said I did quick-scroll a bunch of it. It is its own kind of mind-altering substance, but we have access to mind-bending things.
If you look at my AgentDank repo [1], one could see a tool for finding weed, or you could see connecting world intelligence with SQL fluency and pairing it with curated structured data to merge the probabilistic with the deterministic computing forms. Which I quickly applied to the OSX Screentime database [2].
Vibe coding turned a corner in November and I'm creating software in ways I would have never imagined. Along with the multimodal capabilities, things are getting weirder than ever.
Mr Yegge now needs to add a whole slew of characters to Gas Town to maintain multi-modal inputs and outputs and artifacts.
Just two days I go, I had LLMs positioning virtual cameras to render 3D models it created using the Swift language after looking at a picture of what to make, and then "looking" at the results to see the next code changes. Crazy. [3]
ETA: It was only 14 months earlier that I was amazed that a multi-modal model could identify a trend in a chart [4].
[1] https://github.com/AgentDank/dank-mcp
[2] https://github.com/AgentDank/screentime-mcp
[3] https://github.com/ConAcademy/WeaselToonCadova/
[4] https://github.com/NimbleMarkets/ollamatea/blob/main/cmd/ot-...
The shocking changes to the culture over the last 20 years start to make a lot more sense when you realize someone decided to flood the society with mass quantities of prescription Amphetamines.
By notfromhere 2026-01-0615:281 reply prescription amphetamines don't do this if you are taking the prescribed dose (and you're not getting enough prescribed to get anywhere near high)
Yeah, well, lots of people aren't doing that.
This is instantly recognizable as the work of someone who's been up for a couple days on Adderall.
Of course, there may be other explanations, including other drugs. But if I was one to bet...
By tom_ 2026-01-0618:17 The writing doesn't feel particularly out of character for Yegge, who has always been at least a bit like this. (Though I don't know if that's just him, or drugs as well.)
By bodegajed 2026-01-0612:40 Investors are getting impatient
I mean a higher than average amount of them are, there is a whole psychadelics movement within tech. Just look at Elon Musk and his ketamine usage.
By gertrunde 2026-01-0714:40 Also, Bill Atkinson of Apple fame.
https://news.ycombinator.com/item?id=44530767
(posted here a few months back)
By hungryhobbit 2026-01-0617:041 reply "Lets make extreme generalizations about tens of thousands of people because of an extremely unique outlier (who doesn't even belong to that group of people)."
By zipy124 2026-01-0619:11 Ok fine, here is some data that isn't from a unique outlier:
"Psychedelics are the latest employee health benefit" (tech company) https://www.ft.com/content/e17e5187-8aa7-4564-9e63-eec294226...
"A new psychedelic era dawns in America" (specifically about use in california) https://www.ft.com/content/5b64945f-da21-46d9-853f-c949a95b9...
"How Silicon Valley rediscovered LSD" https://www.ft.com/content/0a5a4404-7c8e-11e7-ab01-a13271d1e...
I could go on, but the knowledge that psychadelic drugs are prominent in the tech community is not a new fact.
By thedrbrian 2026-01-0616:28 They’re the new bitcoin bros.
The article seems to be about fun, which I'm all for, and I highly appreciate the usage of MAKER as an evaluation task (finally, people are actually evaluating their theories on something quantitative) but the messaging here seems inherently contradictory:
> Gas Town helps with all that yak shaving, and lets you focus on what your Claude Codes are working on.
Then:
> Working effectively in Gas Town involves committing to vibe coding. Work becomes fluid, an uncountable that you sling around freely, like slopping shiny fish into wooden barrels at the docks. Most work gets done; some work gets lost. Fish fall out of the barrel. Some escape back to sea, or get stepped on. More fish will come. The focus is throughput: creation and correction at the speed of thought.
I see -- so where exactly is my focus supposed to sit?
As someone who sits comfortably in the "Stage 8" category that this article defines, my concern has never been throughput, it has always been about retaining a high-degree of quality while organizing work so that, when context switching occurs, it transitions me to near-orthogonal tasks which are easy to remember so I can give high-quality feedback before switching again.
For instance, I know Project A -- these are the concerns of Project A. I know Project B -- these are the concerns of Project B. I have the insight to design these projects so they compose, so I don't have to keep track of a hundred parallel issues in a mono Project C.
On each of those projects, run a single agent -- with review gates for 2-3 independent agents (fresh context, different models! Codex and Gemini). Use a loop, let the agents go back and forth.
This works and actually gets shit done. I'm not convinced that 20 Claudes or massively parallel worktrees or whatever improves on quality, because, indeed, I always have to intervene at some point. The blocker for me is not throughput, it's me -- a human being -- my focus, and the random points of intervention which ... by definition ... occur stochastically (because agents).
Finally:
> Opus 4.5 can handle any reasonably sized task, so your job is to make tasks for it. That’s it.
This is laughably not true, for anyone who has used Opus 4.5 for non-trivial tasks. Claude Code constantly gives up early, corrupts itself with self-bias, the list goes on and on. It's getting better, but it's not that good.
By anthonypasq 2026-01-0517:142 reply a response like this is confusing to me. what you are saying makes sense, but seems irrelevant. something like gas town is clearly not attempting to be a production grade tool. its an opinionated glimpse into the future. i think the astethic was fitting and intentional.
this is the equivalent of some crazy inventor in the 19th century strapping a steam engine onto a unicycle and telling you that some day youll be able to go 100mph on a bike. He was right in the end, but no one is actually going to build something usable with current technology.
Opus 4.5 isnt there. But will there be a model in 3-5 years thats smart enough, fast enough, and cheap enough for a refined vision of this to be possible? Im going to bet on yes to that question.
I think this read is generous:
> something like gas town is clearly not attempting to be a production grade tool.
Compare to the first two sentences:
> Gas Town is a new take on the IDE for 2026. Gas Town helps you with the tedium of running lots of Claude Code instances. Stuff gets lost, it’s hard to track who’s doing what, etc. Gas Town helps with all that yak shaving, and lets you focus on what your Claude Codes are working on.
Compared to your read, my read is confused: is it or is it not intending to be a useful tool (we can debate "production" quality, here I'm just thinking something I'd actually use meaningfully -- like Claude Code)?
I think the author wants us to take this post seriously, so I'm taking it seriously, and my critique in the original post was a serious reaction.
By alexjurkiewicz 2026-01-068:49 The blog post says, many times, not to use Gastown. It makes fun of the tool's inconsistent branding and describes a lot of jankiness.
This tool is dangerous, largely untested, and yet may be of interest if you are already doing similar things in production.
By leftbehinds 2026-01-0518:341 reply in 3-5years, sure, just like we are all currently using crypto to pay for groceries and smart contracts for all legal matters.
By anthonypasq 2026-01-0519:044 reply ... no one ever used crypto to buy things. most engineers are currently already using AI. such a dumb comparison that really just doesnt pass the sniff test.
By dzdt 2026-01-0613:38 People use crypto all the time to buy dollars. Thats its main purpose: spend sanctioned rubles to buy crypto to buy dollars; use randomware to coersively obtain crpyto to buy dollars, etc.
Not quite true. This pub's changed hands now but it was possible to pay in bitcoin for several years.
Inside scoop: the pub group who owned that pub (still going, owns four in Cambridge and environs) was cofounded by Steve Early, a Cambridge computer scientist who wrote his own POS software, so it was very much a case of "yeah, that sounds like fun, I'll add it". (Until tax and primary rate risk made it not fun, so it was removed.)
The POS software's on GitHub: https://github.com/sde1000/quicktill
By jbl0ndie 2026-01-140:01 That's brilliant insight, thank you. I enjoyed reading Steve's extensive read me.
Also I'm planning a trip to Cambridge so I've bookmarked one of the pubs for a visit.
By benregenspan 2026-01-060:121 reply For anyone who takes doing their taxes seriously, this is a nightmare. Every pint ordered involves a capital gain (or loss) for the buyer. At a certain point you're doing enough accounting that you might as well be running the bar yourself (or just paying in cash)!
By leipert 2026-01-062:43 Depends. If you hold crypto for more than a year in Germany, gains are tax free.
By Quarrelsome 2026-01-062:18 people use crypto to buy black market goods like drugs. Its incredibly reliable to buy drugs with.
By fragmede 2026-01-0522:30 Their green username is leftbehinds. Let them hold their wrong opinions based on outdated information.
By andrewl-hn 2026-01-0610:012 reply Meanwhile here I am at stage 0. I work on several projects where we are contractually obliged to not use any AI tools, even self-hosted ones. And AFAIK there's now a growing niche of mostly government projects with strict no-AI policy.
By aidanhs 2026-01-1916:46 I'm super interested to hear more on anything you can share about your projects, or the niche of gov projects you're aware of - I've been doing some work with gov and haven't seen this requirement yet, so want to be prepared if it does come up.
(contact details in profile if you prefer)
By mccoyb 2026-01-0612:25 I’m luckily in a situation where I can afford to explore this stuff without the concerns that come from using it within an organization (and those concerns are 100% valid and haven’t been solved yet, especially not by this blog post)
> For instance, I know Project A -- these are the concerns of Project A. I know Project B -- these are the concerns of Project B. I have the insight to design these projects so they compose, so I don't have to keep track of a hundred parallel issues in a mono Project C. On each of those projects, run a single agent -- with review gates for 2-3 independent agents (fresh context, different models! Codex and Gemini). Use a loop, let the agents go back and forth.
Can you talk more about the structure of your workflow and how you evolved it to be that?
I've tried most of the agentic "let it rip" tools. Quickly I realized that GPT 5~ was significantly better at reasoning and more exhaustive than Claude Code (Opus, RL finetuned for Claude Code).
"What if Opus wrote the code, and GPT 5~ reviewed it?" I started evaluating this question, and started to get higher quality results and better control of complexity.
I could also trust this process to a greater degree than my previous process of trying to drive Opus, look at the code myself, try and drive Opus again, etc. Codex was catching bugs I would not catch with the same amount of time, including bugs in hard math, etc -- so I started having a great degree of trust in its reasoning capabilities.
I've codified this workflow into a plugin which I've started developing recently: https://github.com/evil-mind-evil-sword/idle
It's a Claude Code plugin -- it combines the "don't let Claude stop until condition" (Stop hook) with a few CLI tools to induce (what the article calls) review gates: Claude will work indefinitely until the reviewer is satisfied.
In this case, the reviewer is a fresh Opus subagent which can invoke and discuss with Codex and Gemini.
One perspective I have which relates to this article is that the thing one wants to optimize for is minimizing the error per unit of work. If you have a dynamic programming style orchestration pattern for agents, you want the thing that solves the small unit of work (a task) to have as low error as possible, or else I suspect the error compounds quickly with these stochastic systems.
I'm trying this stuff for fairly advanced work (in a PhD), so I'm dogfooding ideas (like the ones presented in this article) in complex settings. I think there is still a lot of room to learn here.
By mlady 2026-01-0221:03 I'm sure we're just working with the same tools thinking through the same ideas. Just curious if you've seen my newsletter/channel @enterprisevibecode https://www.enterprisevibecode.com/p/let-it-rip
It's cool to see others thinking the same thing!
