[HN Gopher] Gas Town: From Clown Show to v1.0
       ___________________________________________________________________
        
       Gas Town: From Clown Show to v1.0
        
       Author : martythemaniak
       Score  : 58 points
       Date   : 2026-04-14 19:18 UTC (3 hours ago)
        
 (HTM) web link (steve-yegge.medium.com)
 (TXT) w3m dump (steve-yegge.medium.com)
        
       | avaer wrote:
       | TBH this post still reads like a clown show.
        
         | righthand wrote:
         | Yeah but the clown show is now marked 1.0 for release.
        
         | moomin wrote:
         | Read some of his earlier stuff. He's a very informal writer,
         | but he's a damn good one with good ideas.
        
           | troupo wrote:
           | No. He _used to be_ good with ideas. Now he 's drinking too
           | much of his own poison. His blog posts are bloviated
           | monstrosities incapable of coherently describing the very
           | trivial ideas contained in them.
        
       | giancarlostoro wrote:
       | I loved Beads, but kept running into issues because it is so git
       | heavy. One: not every system and project I work on uses git. Two:
       | Sometimes I'd switch branches, and that would screw up Beads
       | state entirely. Three: And this is at least last I used it,
       | there's no safety net, Claude would close a Bead, without
       | validating anything.
       | 
       | I wound up building my own with Claude, I made it SQLite first,
       | syncs to GitHub, can pull down from GitHub, and I added "Gates"
       | to stopgap Claude or whatever agent from marking things complete
       | if they've not been: compiled, unit tests run, or simple human
       | testing / confirmation. The Gates concept improved my experience
       | with Claude, all too often it says it finished something, when in
       | fact it did not. Every task must have a gate, and gates must pass
       | before you can close a task. Gates can be reused across tasks, so
       | if "Run unit tests" is one gate, you can reuse it for every task,
       | when it passes, it passes for that one task <-> gate combination.
       | 
       | Anyway, I'm happy for Beads, Gas Town not so much my wheelhouse
       | on the other hand.
        
         | javawizard wrote:
         | Love this.
         | 
         | How did you implement gates? Are they simply tasks Claude
         | itself has to confirm it ran, or are they scripts that run to
         | check that the thing in question actually happened, or do they
         | spawn a separate AI agent to check that the thing happened, or
         | what?
        
           | giancarlostoro wrote:
           | Claude or whatever agent will get a message when it tries to
           | close a task, which tells them which gates are not resolved
           | yet, at which point, the agent will instinctively want to
           | read the task. I did run into an issue where I forgot to add
           | gates to a new project, so Claude did smoosh over by making a
           | blanket gate, I have otherwise never had an issue when I
           | defined what the gate is, Claude usually honors it. I havent
           | worked on big updates recently, but I noticed other tools
           | like rtk (Rust Token Killer) will add their own instructions
           | to your claude's instructions.md file, so I think I need to
           | craft one to tack on with sane instructions, including never
           | closing tasks without having the user create gates for them
           | first.
           | 
           | In a nutshell, a gate is a entry in the DB with arbitrary
           | text, Claude is good about following whatever it is. Claude
           | trying to close a task will force it to read it.
           | 
           | Life's gotten slightly busy, but you can see more on the
           | repo. I've been debating giving it a better name, I feel like
           | GuardRails implies security, when the goal is just to
           | validate work slightly.
           | 
           | https://github.com/Giancarlos/GuardRails
        
             | maleldil wrote:
             | Who closes the gate? Is it Claude itself after it runs the
             | verification? Who makes sure the verification did in fact
             | run?
        
             | skybrian wrote:
             | It sounds like a gate is a prompt that shows up at the
             | appropriate time, which works because LLM's pay more
             | attention to the last thing they read.
             | 
             | It seems like a lot of coding agent features work that way?
        
       | mmastrac wrote:
       | Serious question - there's a lot of fluff talking about Gas Town,
       | but has Gas Town shipping something in public that can be
       | evaluated without all of this surrounding hype and blogposting?
       | 
       | At this point it should be clear that Gas Town has done something
       | we can evaluate the value of.
        
         | rbtprograms wrote:
         | you can always fire it up yourself and see what its all about.
         | in my experience it generates a lot of code very quickly, that
         | code is probably only ever supposed to be LLM maintained, not
         | by people.
        
           | blahblaher wrote:
           | I don't think the op meant Gas Town itself (if they did, my
           | bad), but what has Yegge done with Gas Town? By now it should
           | have released some amazing thing if Gas Town increases
           | productivity so much.
        
             | shermantanktop wrote:
             | What has Yegge done with Gas Town? Well for one, he has
             | posted a bunch of blog content about it which has generated
             | chatter like this and increased his geek mindshare.
             | 
             | Just because he's operating in the realm of smart nerds
             | doesn't mean he is immune to the value-inverting effects of
             | social media.
        
             | panzagl wrote:
             | I think the main thing he's produced using Gas Town is Gas
             | Town itself.
        
           | root_axis wrote:
           | > _you can always fire it up yourself and see what its all
           | about_
           | 
           | I imagine it doesn't run very cheaply.
        
           | drekipus wrote:
           | > _that code is probably only ever supposed to be LLM
           | maintained, not by people._
           | 
           | But LLMs are trying to mimic people. So if confusion is the
           | human response, what's to stop the llm from acting confused?
        
         | dist-epoch wrote:
         | > Having spent six weeks or so using Gas Town across multiple
         | simultaneous projects, I believe I can describe the shift
         | concretely. The bottleneck migrates from coding speed to the
         | rate at which you can generate ideas, write specifications, and
         | validate outputs. You are no longer limited by how fast you can
         | build. You are limited by how fast you can think.
         | 
         | Interesting:
         | 
         | > Kubernetes asks "Is it running?" Gas Town asks "Is it done?"
         | Kubernetes optimizes for uptime. Gas Town optimizes for
         | completion.
         | 
         | https://embracingenigmas.substack.com/p/exploring-gas-town
        
           | Zafira wrote:
           | I'm not sure I find the testimony of a Bain & Company AI
           | consultant (https://www.bain.com/our-team/eric-koziol/) to be
           | compelling for anything outside of generating fees.
        
             | dist-epoch wrote:
             | Does this mean you would avoid an article on PostgreSQL if
             | it's from a company selling Postgres products or
             | consultation?
        
               | Leszek wrote:
               | It means they'd avoid an article on the benefits of
               | smoking if it's posted by a company selling cigarettes.
        
           | mtlynch wrote:
           | This seems to be an AI-generated post where the "author"
           | never reveals building any successful product or even
           | tangible project with Gas Town.
        
             | joezydeco wrote:
             | It's like Web 4.0 zombo.com
        
           | bayarearefugee wrote:
           | This doesn't really answer the question...?
           | 
           | You provided a quote from someone who seems to be an AI-
           | boosting influencer who claimed to use it, but where's the
           | output in the form of code we can look at, or in the form of
           | an app someone can use today?
           | 
           | I'm not an AI-denier. I use LLMs and agentic coding. They
           | increase my productivity.
           | 
           | ...but there is still a very real problem with people
           | claiming that some new way of using AI is earth shattering,
           | and changes everything based on vague anecdotes that don't
           | involve a tangible released output that they can point to.
        
             | tom_ wrote:
             | I don't use LLMs and I never use agentic coding. And I too
             | am interested in an answer to this question.
        
             | tcoff91 wrote:
             | Yeah if this can truly just autonomously make great
             | software, then where is all the new SaaS that is able to
             | undercut incumbents by charging 10-20% of what they are
             | charging?
        
           | torginus wrote:
           | This sounds like every LLM workflow, which is 'you tell the
           | LLM what you want'.
           | 
           | The real distinction is of scale - whether you want a REST
           | endpoint or a fully functional word processor.
           | 
           | But real, actual, complex software is at least half spec
           | (either explicit, or implicitly captured by its code), the
           | question is, can LLMs specify software to the same degree
           | with Gas Town, that you get something functioning?
        
         | _pdp_ wrote:
         | If the post does not have any use-cases proving value then
         | perhaps this is something yet to be validated, i.e. the burden
         | on the users, not the creators.
        
           | IncreasePosts wrote:
           | Corollary: if the post does have use-cases providing value,
           | this is something yet to be validated and the value is just
           | imagine by the author
        
           | RugnirViking wrote:
           | In an era where creating such libraries is much cheaper than
           | validating that they're useful or work, yeah you really
           | should validate it before you expect someone to use it.
           | Nobody is going around trying out every slop project they
           | see, they'd be wasting hours and hours for no gain at all.
           | 
           | This all being said, I do find the idea interesting, but
           | heeded it's advice when it said it's hideously expensive and
           | risky to use. So yes, I do want someone braver, richer, and
           | stupider than me to take the first leap
        
           | en-tro-py wrote:
           | Why would the onus on the value prop be on the user?
           | 
           | There should be no shortage of examples the creator could
           | provide, unless of course...
        
       | solomatov wrote:
       | Does anyone has any tips for starting with Gastown? I am
       | comfortable with couple of agents running, but not yet
       | comfortable with what Gastown offers.
        
         | peddling-brink wrote:
         | Set a budget. Fund an openrouter account with the max you can
         | stomach spending on this test and give it a shot.
         | 
         | At least, that's what I would do, if I had any interest in
         | testing out gastown with my own money. If my employer wants to
         | pay for the testing, that's another question entirely.
        
           | solomatov wrote:
           | I mean not how to do it, it's not that hard, but how to be
           | productive with it.
        
       | bayarearefugee wrote:
       | > But no need to wait. At a high level, Gas City is the answer to
       | all your problems. Ha! At least, for certain classes of problem,
       | such as, "How can I bring AI into my company and pass an audit
       | trail,"
       | 
       | The important audit at my company is conducted by the FDA.
       | 
       | I have a feeling when they ask what processes we followed to
       | mitigate any user harm that could be caused by software changes
       | that "I told an AI-mayor in the form of a cartoon fox what to do
       | and he spit out a bunch of vibecode software written by AI-driven
       | virtual cartoon characters" is not among the answers they want to
       | hear.
        
         | siva7 wrote:
         | Not yet... but me in 2020 telling you what the HN frontpage
         | 2026 would look like you would have sent me to a mental
         | institution, wouldn't you?
        
           | throwup238 wrote:
           | Same institution I'd send Steve today.
           | 
           | The sanatorium from American Horror Story Asylum comes to
           | mind.
           | 
           |  _Dominique, nique, nique..._
        
             | Quarrelsome wrote:
             | we can do better than "that man is crazy". Why not pull up
             | a line in his OPENLY AVAILABLE CODE BASE and mock that
             | instead?
        
               | throwup238 wrote:
               | Beads, his glorified CLI based work tracker, was over
               | _several hundred thousand_ lines of code, last I checked
               | in January.
               | 
               | Where do I even begin to mock that except at the source?
               | That's just absolute insanity.
        
               | Quarrelsome wrote:
               | If its all obviously shit then it shouldn't be that hard.
               | Maybe point Claude at it and ask it to find the most
               | stupid stuff that you can then manually verify as being
               | wtf.
               | 
               | My point is that just calling him names has no substance,
               | but mocking his source specifically does.
        
               | throwup238 wrote:
               | _> If its all obviously shit then it shouldn 't be that
               | hard. Maybe point Claude at it and ask it to find stupid
               | stuff._
               | 
               | What does that even mean? Am I supposed to point Claude
               | at garbage code bases? All it will find is garbage.
               | 
               |  _> My point is that just calling him names has no
               | substance, but mocking his source specifically does._
               | 
               | He is the source. He wrote this stuff under his own
               | volition.
        
               | Quarrelsome wrote:
               | We're supposed to be engineers. Criticising a concept
               | based on conjecture and insult is unbecoming of our
               | culture.
        
               | enraged_camel wrote:
               | What it means is that it is easy to shit on other
               | people's work. Much harder to give constructive criticism
               | - especially on what looks like a throwaway account.
        
           | Avshalom wrote:
           | "every 5th article is about no-code-solutions that sometimes
           | work" might be unexpected but it's hardly the stuff of
           | institutionalization.
        
         | avaer wrote:
         | Keep in mind investing in cartoon foxes was a "business
         | strategy" a lot of (otherwise serious) people bought into in
         | 2020-2021.
         | 
         | And those cartoon foxes didn't even do anything! I guess these
         | ones do?
         | 
         | Don't put it past the masses. These are crazy times.
        
         | Quarrelsome wrote:
         | I did an induction at some ISO certified company some years
         | back, reading their docs. A good 50% of them contained
         | significant content that basically read:
         | 
         | > the thing must be in the place where it should be
         | 
         | With no further information e.g. what place, where, how, when,
         | who facilitates that?
         | 
         | > the person who facilitates it, is the person who facilitates
         | it.
         | 
         | Yea thanks. So their ISO accredited process was basically no
         | process. Would have been way better with a talking fox.
         | 
         | So I feel like humans are capable of just as bad. I'd be
         | interested in what answer the Fox could spit out and I kinda
         | wonder where it might fit on the bell curve of all non Gas-Town
         | "auditable" processes. I'm all for skepticism but I feel like
         | it would be more tangible if we instead criticised the response
         | instead of just conjuring it as "definitely awful" because it
         | happens to be on top of a generated stack.
         | 
         | I mean: I don't want it to work, but maybe we're not as good as
         | we think we are, or the stuff we rate as super important is
         | actually way less important with a generated context. As much
         | as I love good code, the thought that gnaws at the back of my
         | head is the truism that some of the most profitable code in
         | history has been some of the "worst" code (e.g. MySpace's janky
         | code base ontop of ColdFusion or Twitter's "Fail Whale" era).
         | 
         | So I'm happy that someone is exploring this space in an open
         | way. I'm just glad I'm not the one finding that out with my
         | face first.
        
           | vidarh wrote:
           | Which ISO certification matters, but the key thing people
           | should be aware of is that the primary value of the
           | certification to customers is that your processes are
           | _documented_ and that deviations are tracked, so that
           | customers can check whether the processes makes sense before
           | signing a contract. It 's important not to expect the
           | certification itself to guarantee quality.
        
         | cma wrote:
         | > The important audit at my company is conducted by [Trump's
         | second term] FDA.
         | 
         | Could work
        
       | ncruces wrote:
       | The original Beads, it seems, used my CGO-free SQLite driver.
       | 
       | Seems like I'm back to obscurity.
       | 
       | :)
        
         | a_t48 wrote:
         | You got relegated to a stack of dirty stacked up crates,
         | according to the genAI article images.
        
       | pianopatrick wrote:
       | I searched on google about the cost of running Gas Town. The
       | Gemini AI response claimed Gas town costs $100 / hour and can
       | spit out 4000 lines of code per hour, so Gas Town costs 2.5 cents
       | per line of code.
       | 
       | I tried tracking down where those numbers came from and the
       | sources were a bit sketchy. Can anybody who has used Gas Town
       | confirm those numbers, or report their personal numbers?
        
         | peddling-brink wrote:
         | Using regular Claude code I can generate 4k lines an hour.
         | Using some bash I can generate 4k lines of code per second.
         | 
         | Lines of code per hour is a bad metric.
         | 
         | Can it solve a problem using production quality code that
         | doesn't take four times as long to review? That sounds like
         | something I would pay $100 for.
        
           | tom_ wrote:
           | I think the point is that we are given no real idea at all,
           | not even some ballpark figures, about how much actual money
           | actually needs to be spent in order to run Gas Town. The
           | original article had some handwavy stuff about how it cost An
           | Awful Lot, but no actual numbers.
           | 
           | Cost per line of code is not an amazing metric, but at least
           | it's an attempt to come up with a figure.
           | 
           | (I would also be interested to find out how much it costs to
           | run...)
        
           | pianopatrick wrote:
           | Well, yes ideally we would eventually also have metrics about
           | error rates and reject rates. Like ideally at some point
           | someone could do a study of "for every 100 PRs Gas Town
           | generates, how many are accepted after code review and how
           | many are rejected" or "for every 100 lines of code Gas Town
           | generates, how many coding errors are detected by human
           | reviewers".
           | 
           | Unfortunately I think things are moving so fast that by the
           | time such a study was done, we would already be on to newer
           | models and newer versions of gas town.
        
       | throw1234567891 wrote:
       | Does this support OpenAI-compatible APIs? Or is it only
       | clowncode, codex and copilot? Love to try it but without OpenAI-
       | compatible APIs it is junk.
        
       | vessenes wrote:
       | Nice timing. I was just noting that beads in an old repo, just
       | ... worked. Updates worked, I didn't have super weird errors to
       | track down... I was like "nice!" Beads bumping to 1.0 is great. I
       | haven't used gas town in a month or so, but a stable gas town
       | sounds very valuable.
       | 
       | I think Yegge's instincts that making a programmable / editable
       | coordination layer (he calls this gas city) is a great idea. Gas
       | town early days was definitely a wild experience in terms of
       | needing to watch carefully lest your system be destroyed, and
       | then I put that energy into OpenClaw - I'll probably spin up Gas
       | City and see what it can do soon though. Very cool.
        
       | cdrnsf wrote:
       | An apt name for something doing it's part to spike energy
       | consumption and accelerate the climate crisis.
        
         | Quarrelsome wrote:
         | The climate crisis is primarily a consequence of fossil fuels,
         | not necessarily energy demand. I feel like its a poor
         | conflation, despite it possibly being a truism depending on
         | where the datacentre is based and what power source feeds it.
        
           | cdrnsf wrote:
           | If we're keeping gas and coal plants online to power this or
           | using gas generators to power data centers, I'd consider that
           | a wasteful contributing factor.
        
             | Quarrelsome wrote:
             | but we could also argue that not investing in extra non-
             | fossil fuel capacity is the issue here. OR not investing in
             | more research on super conductors and/or storage. Iceland
             | could possibly export considerable amounts of renewable
             | energy if we licked those problems.
             | 
             | I mean, under the same logic couldn't we kinda argue that
             | TV has ruined the planet? A lot of energy for something of
             | debatable physical value. OR Motor racing, football, The
             | Olympic games? All that energy and waste just to find out
             | who can throw a stick the furthest every four years.
        
               | cdrnsf wrote:
               | I suppose one could, but none of those are primary
               | economic drivers with dim prospects for turning a profit
               | (well, I suppose that may be true of TV).
        
       | sailingparrot wrote:
       | Gas Town really feels not just vibe coded but also vibe designed.
       | I looked into it, to see whether multi agent setups really made a
       | difference, the entire design philosophy feels like it was <<
       | let's add one more layer of agent and surely this time it will
       | work >> about 10 times in a row.
       | 
       | So now you have agents of type mayor, polecats, witnesses,
       | deacons, dogs etc plus a slew of Unneeded constructs with
       | incomprehensible names.
       | 
       | In one of the blog post for gas town I remember reading something
       | by the author along the lines of << it's super inefficient, but
       | because you burn so many tokens, you still get what you want at
       | the end! >> clearly this is also the design philosophy behind
       | this project, just (get your ai to) throw more random
       | abstractions and more agent types until you feel like it kinda
       | works, don't bother asking yourself if they actually contribute
       | anything.
       | 
       | This gave me the very clear feeling that most of the complexity
       | of gas town is absolutely not needed and probably detrimental.
       | 
       | Ended up building my own thing that is 10x simpler, just a simple
       | main agent you talk to, that can dispatch subagents, they all
       | communicate, wake each other up and keep track of work through a
       | simple CLI. No << refinery >> or << wasteland >> or << molecule
       | >> or << convoys >> or << deacons >> or ...
        
         | rspeele wrote:
         | > Ended up building my own thing that is 10x simpler, just a
         | simple main agent you talk to, that can dispatch subagents,
         | they all communicate, wake each other up and keep track of work
         | through a simple CLI. No << refinery >> or << wasteland >> or
         | << molecule >> or << convoys >> or << deacons >> or ...
         | 
         | You won't get 10k stars and a blog post out of that. Obviously
         | you need some Stoats who have Conferences with the Stump Lord
         | to determine whether they are needed at the Silo or the Bilge.
         | They'll then regroup at the appropriate Decision Epicenter and
         | delegate to the Weasels and Chipmunks who actually do the
         | coding (antiquated term) in the Salt Mine.
         | 
         | The Stump Lord is an owl.
        
           | cachius wrote:
           | Reminds me of Urbit the completely exotic computer network
        
             | actionfromafar wrote:
             | That's fully veered into cult territory.
        
       | winstonp wrote:
       | Yegge is a snake oil salesman
        
         | dang wrote:
         | Please don't post personal attacks to HN. It's not what this
         | site is for, and destroys what it is for.
         | 
         | Thoughtful critique is of course fine but there's no need to be
         | personal, and it should be something we can learn from.
         | 
         | https://news.ycombinator.com/newsguidelines.html
        
           | karmakaze wrote:
           | Does the apparent rugpull on the $GAS meme coin[0] qualify?
           | 
           | [0] https://en.wikipedia.org/wiki/Steve_Yegge#Vibe_coding_and
           | _cr...
        
             | actionfromafar wrote:
             | To me, no, not quite. I'll give him _one_ free pass. More
             | like _" I'll coast on this pulled rug to see what happens"_
             | than that _he_ did the rug pull. Not a very wise thing to
             | do, but not malicious either.
        
             | 0xbadcafebee wrote:
             | The description on Wikipedia looks like somebody else
             | created a memecoin in his honor, sent him the profits, and
             | he accepted them? And the only people harmed were people
             | who invest in random memecoins? I don't understand the
             | problem.
        
       | dbbk wrote:
       | I tried Beads and it kept breaking in such frustratingly random
       | ways that I just added a Linear MCP server and called it a day.
       | That's really all you need.
        
         | CharlesW wrote:
         | I've been using Beads for 5 different projects, and Beads
         | and/or Dolt failures have been a regular thing. It's own
         | "doctor" feature is sort of disturbing, in that it (1) tells me
         | that my Beads setups are always at least a little bit broken,
         | but (2) can never fix all of the issues. Hopefully the 1.0
         | designation means that Steve is out of "throw shit at the wall"
         | mode. Beads is fine as a replacement for Markdown files, but
         | I'll never go near Gas Town because of my experience with it.
        
       | munificent wrote:
       | _> I've been saying since last year that by the end of 2026,
       | people will be mostly programming by talking to a face. There's
       | absolutely NO reason to type with the Mayor. You should be able
       | to chat with them like a person. You'll have a cartoon fox there
       | onscreen, in costume, building and managing your production
       | software, and showing you pretty status updates whenever you ask
       | for one. This is the end state for IDEs._
       | 
       | This is a desirable end state for highly social but perhaps
       | slightly sociopathic extroverts who want to spend all day talking
       | even though they aren't talking to a person.
       | 
       | For anyone else, it's hard to imagine considering that a
       | desirable way to spend eight hours a day.
        
       | 0xbadcafebee wrote:
       | Beads is cool, but I tried to use it, and the backend didn't
       | really make sense. I have to run an sql database in the
       | background? How does it sync with Git? (I didn't see any
       | files/objects committed to the repo) Plus, Dolt ended up using a
       | constant 3-30kB/s of i/o in the background, while nothing was
       | actually going on. That and Beads has a lot of features I'm not
       | gonna use. All of this was just too complicated for my tiny
       | brain.
       | 
       | So I slapped together my own Beads implementation
       | (https://codeberg.org/mutablecc/dingles) over a day or two.
       | Probably has bugs, and I'm sure race conditions if you tried to
       | use with Gas Town, and likely does not scale. But it has the
       | minimum functionality needed to create and track issues and sync
       | them (locally and remotely, either via normal merge, or a
       | dedicated ticket branch). No SQL, no extra features, just JSONL
       | and Git. Threw a whole large software project at it, and the AI
       | took to it like a duck to water, used it to make epics for the
       | whole project, methodically worked through them all, dependencies
       | first, across multiple context sessions. The paradigm of making
       | tools the AI wants to use is clearly a winner.
        
       | pron wrote:
       | Does Yegge really think that building production software this
       | way is a good idea?
       | 
       | Let's assume that managing context well is a problem and that
       | this kind of orchestration solves it. But I see another problem
       | with agents:
       | 
       | When designing a system or a component we have ideas that form
       | invariants. Sometimes the invariant is big, like a certain grand
       | architecture, and sometimes it's small, like the selection of a
       | data structure. Eventually, though, you want to add a feature
       | that clashes with that invariant. At that point there are usually
       | three choices:
       | 
       | * Don't add the feature. The invariant is a useful simplifying
       | principle and it's more important than the feature.
       | 
       | * Add the feature inelegantly or inefficiently on top of the
       | invariant. Hey, not every feature has to be elegant or efficient.
       | 
       | * Go back and change the invariant. You've just learnt something
       | new that you hadn't considered that put things in a new light,
       | and there's a better approach.
       | 
       | Often, only one of these is right. Usually, one of these is very,
       | very wrong, and with bad consequences.
       | 
       | But picking among them isn't a matter of context. It's a matter
       | of judgment and the models - not the harnesses - get this
       | judgment wrong far too often (they go with what they know - the
       | "average" of their training - or they just don't get it). So
       | often, in fact, that mistakes quickly accumulate and compound,
       | and after a few bad decisions like this the codebase is
       | unsalvageable. Today's models are just not good enough (yet) to
       | create a complete sustainable product on their own. You just
       | can't trust them to make wise decisions. Study after study and
       | experiement after experiment show this.
       | 
       | Now, perhaps we make better judgment calls because we have
       | context that the agent doesn't. But we can't really dump
       | everything we know, from facts to lessons, and that pertains to
       | every abstraction layer of the software, into documents. So even
       | if it is a matter of context, it is not something that can be
       | solved with better context _management_.
        
       | siliconc0w wrote:
       | My experience is that Agentic Coding can legitimately get you
       | mostly-working software. You do, however, still need to spend a
       | few days groking, validating, and usually nudging/whacking it to
       | conform to the shape you intended vs what the agent inferred.
       | 
       | It is pretty magical to go from brainstorming an idea in the
       | evening, having ChatGPT Pro spit out a long list of beads to
       | implement it, leaving it running over night in a totally empty
       | repo and waking up to a mostly-implemented project.
        
       ___________________________________________________________________
       (page generated 2026-04-14 23:00 UTC)