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 roadmap and get better productivity than an engineer. This is not whimsical to me, I’m getting burnt out trying to navigate the absurd expectations of investors and executives with the real world engineering concerns of my day to day job.
> horrified to come to the HN comments and LinkedIn comments proclaiming Gastown as the future of engineering.
I don't spend much time on LinkedIn, but basically every comment I've read on HN is that, at best, Gas Town can pump out a huge amount of "working" code in short timeframes at obscene costs.
The overwhelming majority are saying "This is neat, and this might be the rough shape of what comes next in agentic coding, but it's almost certainly not going to be Gas Town itself."
I have seen basically no one say that Gas Town is the The Thing.
I feel that yegge captured the mania of the whole operation rather well. If your bosses commit to the idea that 100 memoryless stochastic "polecats" will deliver a long term sustainable business, then there are probably other leadership issues besides this.
I think Steve's idea of an agent coordinator and the general model could make sense. There is a lot of discussion (and even work from Anthropic, OpenAI, etc) around multiagent workflows.
Is Gas Town the implementation? I'm not sure.
What is interesting is seeing how this paradigm can help improve one's workflow. There is still a lot of guidance and structuring of prompts / claude.md / whichever files that need to be carefully written.
If there is a push for the equivalent of helm charts and crds for gas town, then I will be concerned.
I ran into this building a similar workflow with LangGraph. The prompt engineering is definitely a pain, but the real bottleneck with the coordinator model turns out to be the compounding context costs. You end up passing the full state history back and forth, so you are paying for the same tokens repeatedly. Between that and the latency from serial round-trips, it becomes very hard to justify in production.
AI is such a fun topic -- the hype makes it easy to loath, but as a coder working with Claude I think it's an awesome tool.
Gastown looks like a viable avenue for some app development. One of the most interesting things I've noticed about AI development is that it forces one to articulate desired and prohibited behaviors -- a spec becomes a true driving force.
Yegge's posts are always hyperbolic and he consistently presents interesting takes on the industry so I'm willing to cut him a buttload of slack.
I agree, it is really interesting. I think that the main reason, though, is that instead of a waterfall cycle taking weeks or months, it now takes minutes. So it’s the process of waterfall (speccing things out carefully in advance, committing to the plan, assessing the results based on adherence to the plan, etc), but on the time frame of agile.
Embrace and use it to your advantage. Tell them nobody knows and understands how these things will actually work long term, that's why there's stuff like gas town, and that the way you see all of this is you can manage this process. What you bring to the table is making sure it will actually work if the tech is safe and sound, reaping the rewards, or protect the business if the tech fails, protecting the company from catastrophic tech failure, telll them that you are uniquely positioned to carry out the balancing act because you are deep in the tech itself. bonus if you explain the uncertainty framing in the business strategy: "because nobody really understands the tech nobody has an advantage, we are all playing on a leveled field, from the big boys at FAANGs to us peasants in normal non-tech enterprises: I am your advantage here if you give me the tools and leverage I need to make this work". if you play this right you'll get the fat bonus whether the tech actually works or not.
"I’m getting burnt out trying to navigate the absurd expectations of investors and executives with the real world engineering concerns of my day to day job."
Welcome to being a member of a product team who cares beyond just whats on their screen... Honestly there is a humbling moment coming for everyone, it and Im not sure its unemployment.
Strong agreement with this. The whimsical, fantasy, fun, light hearted things are great until a large enough group of people take them as a serious life motto & then try to push it on everyone else.
Taking the example of the cryptocurrency boom (as a whole) as the guide, the problem is the interaction of two realities: big money on the table; and the self-fulfilling-prophecy (not to say Ponzi) dynamic of needing people to keep clapping for Tinker-bell, in greater and greater numbers, to keep the line going up. It corrupts whimsical fun and community spirit, it corrupts idealism, and it corrupts technical curiosity.
And FOMO stories about missing out on Bitcoin when he knew about it, so he doesn't want you to miss out on this new opportunity to get "filthy rich" as an "investor" while you still can.
This initially sunk my heart, but in all his replies there are like 50 very clearly unintelligent crypto grifters telling him he needs to be killed for scamming them, so I am unsure who to root for at this point. It's depressing he accepted it, but I might partially forgive it due to him making a lot of them lose money.
Why is it hard to criticize people for being part of a scam operation? It's so morally and ethically bankrupt that it's really easy and valid to criticize someone for
Who is being scammed? The only people buying into tokens as obscure as these are degenerate gamblers who know very well that it's not any kind of an investment.
It's absolutely marketed as an investment, and solely used and referenced by people saying it is an investment. This is like saying those cannabis paraphernalia shops are marketed as only for tobacco.
But people do. There are people who genuinely think crypto is an investment. Yes, smart people knows it is just a grift and that it is just about selling it on to the next person before it crashes. But is it moral to make money on stupid people? Many people lose all their money on gambling even if we always known gambling is a loss.
You don't have to be smart to understand they're very, very, very obviously saying it's an investment and using extremely superficial cover. All things like these are exclusively pennystock scams.
You're being bamboozled. Google the name of it. Search it on Twitter and 4chan. Watch any Coffeezilla video.
I'm googling "bags.fm", everything I can find is about money going to creators. Literally nothing suggesting that you're going to get rich by buying these tokens.
Searching for "bags.fm" on X with keywords like "invest" or "rich" or "moon" also does not seem to return any conversations referring to anyone but the creators getting rich.
I can't find any bags.fm references on 4chan, and searching for gas town instead doesn't seem to bring up anything cryptocurrency related in the archive.
> You're being bamboozled
I don't think so. I suspect the world is so full of crypto scams that when someone does something explicitly non-scammy ("Hey, here's a crypto thing you can use to give me free money!") people still incorrectly view it as scammy because of crypto.
How many memecoin "investors" do you think view these as serious investments? I suspect essentially none of them.
How many memecoin "investors" are degenerate gambling addicts who need treatment? Probably most of them.
Taking money from vulnerable gambling addicts is certainly not ideal, but it's far from scammy.
Yegge himself wrote a blog post to his non crypto audience calling it an investment that he hopes makes its investors filthy rich. He pumped it, then he dumped it, and announced he’s walking away from it at that point after taking his profits and crashing its value.
I don’t know why you’re talking about existing hardcore BAGS addicts when the topic is Yegge promoting a crypto grift to his own general audience as an investment and then running the typical pump and dump scam on them.
100% of these things are somewhere on the scam and fraud spectrum. An unscrupulous person creates a token or a platform for creating tokens with the goal of raising the worthless token's price so they can parasitically make millions from something that holds zero value.
The "fund creators" thing is a common ploy. If they actually wanted to do that, they'd make it so you can only donate with dollars or stablecoins.
I don't get crypto - just looked up how a couple of most performant stocks did in the past decade, and I'm pretty sure you could outperform BTC with the same amount of risk tolerance.
The swings on BTC price are absolutely insane, and ETH even more so (which is even more risky, without showing higher gains).
People keep giving him the benefit of the doubt. "He's clearly on to something, I just don't know what". I know what. The hustle of the shill. He has long gone from 'let's use a lot of tokens' to seeking a high score. He disgusts me.
I too am a Very Serious Engineer but my shock is in the other direction: of course the ideas behind Gas Town are the future of software development and several VSEs I know are developing a proper, robust, engineering version of it that works. As the author of this article here remarks “yes, but Steve did it first”, and it annoys me that if I had written this post nobody would have read it, but also that, because I intend to use it in Very Serious Business ($bns) my version isn’t ready to a actually be published yet. Bravo to Steve for getting these thoughts on paper and the idea built even in such crude form. But “level 8” is real and there will be 9s and 10s and I am really enjoying building my own.
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.
