It describes a team spending 30x payroll on tokens - $3,000,000 in token spend per month - building a multiplayer game where incidents and bug reports from users are passed directly to Fable 5/5.1 agents who then act on them and deploy the changes to production.
"We consider it an outage if we don't ship every hour"
It's worth reading because it's either a complete disaster or a glimpse of the future, or quite possibly both.
lnwlebjel 11 minutes ago [-]
This is amazing and somewhat insane. It's more like they are building an organism with an immune system than a code base. Interesting that they say only Fable works for them.
theturtletalks 6 minutes ago [-]
I’m building the same but with a malleable SaaS. Basically when you sign up, you get the software deployed and an agent that can control that deployment and code.
But the process is slow. The user wants to add a feature to their app so they ask the AI. The AI has access to a terminal where it can clone, fix, and push. This takes time and isn’t instant.
Once AI can abstract this part, software will change forever. It’s what this post alludes to, does code, PR, etc need to reinvented for this?
Once so, no one would ever use cookie cutter software because you could build your own and maintain it using just an agent.
ngruhn 17 minutes ago [-]
So as a user I can basically deploy code through bug reports? Sounds like a prompt injection nightmare.
dcss_gardener 7 minutes ago [-]
I'm both fascinated and appalled by the metagaming implications. Can I guide fable into subtly rebalancing a game in favor of my preferred play style?
simonw 3 minutes ago [-]
Their argument seems to be that Fable 5/5.1 are smart enough to avoid being subverted in this way. I'm skeptical!
rbtprograms 27 minutes ago [-]
well, i did go check out the company spawn from the article. its certainly interesting how hands off their process is and how much they ship, but holy shit the games were fucking horrible. there was a direct WoW ripoff (right down to the assets) that was unplayable, a racing simulator where my controls stopped working 10 second in, and some sort of RPG that i started and just never loaded. so i will take what they are saying with the heaviest possible grain of salt.
dcss_gardener 5 minutes ago [-]
Yes exactly this is my standard for everything now. You can spend an unbelievable amount of tokens doing all kinds of things that are interesting as processes in their own right.
But is the outcome good? Is the game fun?
rbtprograms 23 seconds ago [-]
at the end of it: is anything of value delivered to customers? the company might say "well users make the games with AI, we just serve them and host the multiplayer." okay, but again, what value was created? they brag about being one of anthropic's top customers; congrats you are handing VC money to anthropic. why should i care? theres no answer for why anyone should care, because to them the system and clout is the product, the product doesnt actually matter.
at least thats my read on it. i dont know how else to understand whats going on here.
dgritsko 51 minutes ago [-]
Was thinking of that exact article while I was reading this, we must be following the same folks. Highly recommend folks reading it, even if it feels insane in some regards it's a fascinating look at what the limits of this stuff could be and I found myself with a lot of new ideas to consider after reading it. Interesting times.
Edit - after writing "we must be following the same folks" I realized that you are, in fact, Simon Willison - I saw this article because you posted about it on X, haha.
moecables 11 minutes ago [-]
so if there's no user reports and fable isn't shipping in the middle of the night, then it's an outage?
KasianFranks 40 minutes ago [-]
This works as we've been doing it since Opus 4.5 (Nov 2025) with every user request, feature and bug. It's the future without a doubt. The feedback loops evolve and get stronger depending on how well you fine-tune or train your system to optimize on its own.
throwaway5752 6 minutes ago [-]
"We consider it an outage if we don't ship every hour" is the dumbest thing I've ever read.
I really mean this. Does it benefit the business? Does it benefit the users? When you optimize for the wrong thing, you inevitably fail.
kg 31 minutes ago [-]
This from that tweet stood out to me: "In general, we've seen that OpenAI's models game their own checks"
In the past when working on agentic stuff I've observed models gaming checks aggressively, to the point that when we were validating log files to see what the agent had done, the agent responded by editing the log files to pass validation. I can only imagine how bad that kind of behavior is at scale, and it sounds like they ran into it.
jbvlkt 1 minutes ago [-]
For the argument lets say that this approach works and results in high quality apps. But will be users happy that app is updated 3 times a week and all updates add major changes? Because code generation is so cheap and fast it means we should even more thing about what to build to not overwhelm our users and actually solve their problems.
juancn 27 minutes ago [-]
Not a single mention of value or revenue.
Only three metrics went up: LOC, token spend and presumably release speed/frequency.
What's the markup (profit/COGS)? is it up?
Customer satisfaction? Is NPS moving one way or another?
rbtprograms 21 minutes ago [-]
none of these types of pieces of content focus on what was created for users, its always about how sky high their "shipping" metrics are (PRs merged, LoC, etc). it makes it extremely hard for me to care, as they all boil down to "im a dev who made some loops on loops on loops that writes a lot of code and spends a lot of tokens."
i will say, at least this article says "we merge 5x more and our revert rate has stayed the same." so thats at least a metric i can start to respect
npodbielski 26 minutes ago [-]
They probably did not even think about asking customers.
erminpour 2 hours ago [-]
Maybe it's just me, but "How much we ship per engineer" doesn't seem like the correct metric to track.
If that's the benchmark, developers are incentivized to produce over-engineered and bloated code.
ngruhn 11 minutes ago [-]
Won't there also be a point were you're shipping so fast that that in itself deteriorates UX? What if a page literally changes every time I reload? What if it changes mid-checkout process and the deal I agreed to 5 seconds ago does not exist anymore?!
ActionHank 1 hours ago [-]
Categorically, if you ship more bugs per engineer, you fix more bugs per engineer.
zamalek 2 hours ago [-]
I have come to realize that code (and I think possibly productivity in general) being expensive was always a feature. I am sure that a few great ideas did get lost to obscurity due to lack of access to resources to build them out. However, we now have an absolute deluge of complete and utter shite.
intelVISA 28 minutes ago [-]
Agreed, for the individual LLMs can be powerful to let less technical folks build and customize their software - at an org level I reckon we'll start seeing more sinking ships as that bottleneck was actually helpful at limiting the flow of lackluster features to prod.
moecables 9 minutes ago [-]
yeah shipping widgets and shit, not real features
dominotw 2 hours ago [-]
Yep and there is no real demand for slop engineers are producing anyways.
simonw 60 minutes ago [-]
It this point, a whole lot of teams have been leaning into AI-first, not-entirely-reviewed code since around March this year.
That means we are already 6-8 months in, and not far from having a full year of experience of what that actually looks like, albeit weirdly influenced by the increase in model capabilities during that period.
I'm looking forward to those retrospectives. Did this turn out to work OK for the teams doing it? What were the biggest failings and/or surprises? With hindsight, did this produce good quality software?
lumost 46 minutes ago [-]
I think the biggest shift is in predictability. Will something be done today, next week, or next month - nobody knows. Will we converge on a bug free state? not sure.
So far AI works great at fast moving work which you will probably recode or throw away in a month or two anyway (e.g. a startup) but is weak at maintaining a large code base that you rely on. At least part of this is cultural, as the cost of misalignments between team members can be quickly translated into broken software.
wild_egg 43 minutes ago [-]
I don't disagree but
> Will we converge on a bug free state?
I have never witnessed this state in my two decades of software work. Why would we think AI will magically achieve this?
kg 26 minutes ago [-]
Software robustness, at least in terms of "has the app crashed on any client machines today", is achievable. It's just expensive enough to achieve that most people (rightly or not) don't prioritize it, and the more moving parts (like third party libraries or language runtimes) your application has the harder it is to achieve. Maybe AI will lower the cost of achieving that.
When I worked on Guild Wars every server or user crash went to a shared inbox and was bucketed so we could identify and act on new crashes. IIRC we maintained very, very low production crash rates and could prove that many of the crashes were due to hardware faults.
Similarly, Mozilla tries to analyze and act on every crash report they get in the field. If a webpage visited by even a small % of the customer base was causing crashes, the team worked to try and fix the crash to deliver stability. If it was a high-traffic webpage it got treated as a high-priority task - I remember Farmville breaking was basically a 3-alarm fire back when it was extremely popular.
"No bugs at all" is an even higher bar, but it probably is possible for simpler applications with the use of stuff like theorem provers. I'd love to see someone try it in production but I think the return on investment for that is probably super super negative.
KasianFranks 33 minutes ago [-]
Have been at it since Nov 23rd 2025 with a first commit with Opus 4.5 - it was rough at first but after about year well worth it. You can also tell where so many just get stuck in the mud due to lack of direct experience with all the engineering silos (from bare metal sys admin to QA eng silos outside of standard software engineering core) it takes to roll out a new kind of technology company while scaling a new kind of commercialization model, also managed by AI and AI native from the ground up.
mirmor23 2 hours ago [-]
Spent few minutes reading the infomercial -- regretted it. Engineering principles form the bedrock first, and AI-tools are made to fit in them, not the other way around as this infomercial propounds. Its linkedin vibe is a big turnoff too.
MrBuddyCasino 7 minutes ago [-]
Thanks, this is exactly right. AI is useful insofar it can be made to conform to engineering principles.
nater5000 2 hours ago [-]
This post is funny to me, because I feel it falls well short of what a proper, forward-thinking "AI-native" engineering org would actually look like. That is, the author is presenting this as kind of a radical departure from normal engineering, but I just see it as normal engineering with more AI. I don't see that as AI-native.
To me, true "AI-native" engineering will be one where questions regarding how humans will do things like review code are irrelevant. You explicitly throw away any concept of typical software engineering and, instead, differ to the AI. Your job, as a human, is solely to do what the AI can't physically do. That's not the same as closing gaps between what AI is currently capable of doing and what you'd need it to be capable of doing. It's literally enforcing that anything an AI is able to do is treated as correct in itself, and you, as a human, only support it by being a human.
If that sounds outlandish, that's because it is. We don't have such capable AI systems yet. It's possible we never will. But that's beyond the point. The reality is trying to make an "AI-native" engineering org by just layering AI on top of existing processes and systems is futile. If your expectation is that AI will continue to improve in capabilities at an accelerating rate, then these stop-gaps are pointless. You might as well just ignore AI altogether until it is able to completely take over, because that's the inevitable goal, right?
If you're willing to buy that will be possible, then my guess is that it will occur in the form of small scale startups and actual mavericks rather than someone trying to run an existing business who will simply be too risk adverse to go all in when the time comes. Some guy in his basement is more likely to leverage AI "properly" to build an actual "AI-native" engineering org because that person won't have much to lose.
satvikpendem 53 minutes ago [-]
Reminds me of a few things, like being a meat proxy, as well as books like Company of One or Million Dollar One Person Business, and these were published before AI so right now we will see companies with only one founder and hundreds to thousands of AI agents. There already was that drug delivery company with the one founder but apparently a lot of their revenue was fraudulent. Still, it proves the point that it is possible.
Eridrus 2 hours ago [-]
I think this is all fair, but somewhat just semantics.
Most engineers are working in "normal" engineering orgs, but can feel the ground underneath them shifting, and companies believe that if they are caught flat footed, they will be out competed in the marketplace, so they are all trying to make sure they are adopting it at least in a way that lets them keep pace if not accelerate revenue.
If you are not impacted by economic incentives, you can continue to not care about this transitional state, but most people do.
9 minutes ago [-]
2 hours ago [-]
fleetml 1 hours ago [-]
Nice work. How do you handle swapping in a new model version, hot reload or restart? And what happens to a batch that's mid-run when it changes?
sellmesoap 2 hours ago [-]
In my best impression of the slapchop guy:
First you take your Blendtech and "will it blend" your engineers, then upload the result to the cloud inside what is called an S3 bucket (don't forget to set access permissions on your buckets kids!) to be digested by the clankers, sit back and profit!
Dark humor aside I think disconnecting a bunch of problem solvers from their computing equipment could really enhance the world, putting that analytical power into the world in person could move a lot of cogs, rather then marshalling JSON.
It describes a team spending 30x payroll on tokens - $3,000,000 in token spend per month - building a multiplayer game where incidents and bug reports from users are passed directly to Fable 5/5.1 agents who then act on them and deploy the changes to production.
"We consider it an outage if we don't ship every hour"
It's worth reading because it's either a complete disaster or a glimpse of the future, or quite possibly both.
But the process is slow. The user wants to add a feature to their app so they ask the AI. The AI has access to a terminal where it can clone, fix, and push. This takes time and isn’t instant.
Once AI can abstract this part, software will change forever. It’s what this post alludes to, does code, PR, etc need to reinvented for this?
Once so, no one would ever use cookie cutter software because you could build your own and maintain it using just an agent.
But is the outcome good? Is the game fun?
at least thats my read on it. i dont know how else to understand whats going on here.
Edit - after writing "we must be following the same folks" I realized that you are, in fact, Simon Willison - I saw this article because you posted about it on X, haha.
I really mean this. Does it benefit the business? Does it benefit the users? When you optimize for the wrong thing, you inevitably fail.
In the past when working on agentic stuff I've observed models gaming checks aggressively, to the point that when we were validating log files to see what the agent had done, the agent responded by editing the log files to pass validation. I can only imagine how bad that kind of behavior is at scale, and it sounds like they ran into it.
Only three metrics went up: LOC, token spend and presumably release speed/frequency.
What's the markup (profit/COGS)? is it up?
Customer satisfaction? Is NPS moving one way or another?
i will say, at least this article says "we merge 5x more and our revert rate has stayed the same." so thats at least a metric i can start to respect
If that's the benchmark, developers are incentivized to produce over-engineered and bloated code.
That means we are already 6-8 months in, and not far from having a full year of experience of what that actually looks like, albeit weirdly influenced by the increase in model capabilities during that period.
I'm looking forward to those retrospectives. Did this turn out to work OK for the teams doing it? What were the biggest failings and/or surprises? With hindsight, did this produce good quality software?
So far AI works great at fast moving work which you will probably recode or throw away in a month or two anyway (e.g. a startup) but is weak at maintaining a large code base that you rely on. At least part of this is cultural, as the cost of misalignments between team members can be quickly translated into broken software.
> Will we converge on a bug free state?
I have never witnessed this state in my two decades of software work. Why would we think AI will magically achieve this?
When I worked on Guild Wars every server or user crash went to a shared inbox and was bucketed so we could identify and act on new crashes. IIRC we maintained very, very low production crash rates and could prove that many of the crashes were due to hardware faults.
Similarly, Mozilla tries to analyze and act on every crash report they get in the field. If a webpage visited by even a small % of the customer base was causing crashes, the team worked to try and fix the crash to deliver stability. If it was a high-traffic webpage it got treated as a high-priority task - I remember Farmville breaking was basically a 3-alarm fire back when it was extremely popular.
"No bugs at all" is an even higher bar, but it probably is possible for simpler applications with the use of stuff like theorem provers. I'd love to see someone try it in production but I think the return on investment for that is probably super super negative.
To me, true "AI-native" engineering will be one where questions regarding how humans will do things like review code are irrelevant. You explicitly throw away any concept of typical software engineering and, instead, differ to the AI. Your job, as a human, is solely to do what the AI can't physically do. That's not the same as closing gaps between what AI is currently capable of doing and what you'd need it to be capable of doing. It's literally enforcing that anything an AI is able to do is treated as correct in itself, and you, as a human, only support it by being a human.
If that sounds outlandish, that's because it is. We don't have such capable AI systems yet. It's possible we never will. But that's beyond the point. The reality is trying to make an "AI-native" engineering org by just layering AI on top of existing processes and systems is futile. If your expectation is that AI will continue to improve in capabilities at an accelerating rate, then these stop-gaps are pointless. You might as well just ignore AI altogether until it is able to completely take over, because that's the inevitable goal, right?
If you're willing to buy that will be possible, then my guess is that it will occur in the form of small scale startups and actual mavericks rather than someone trying to run an existing business who will simply be too risk adverse to go all in when the time comes. Some guy in his basement is more likely to leverage AI "properly" to build an actual "AI-native" engineering org because that person won't have much to lose.
Most engineers are working in "normal" engineering orgs, but can feel the ground underneath them shifting, and companies believe that if they are caught flat footed, they will be out competed in the marketplace, so they are all trying to make sure they are adopting it at least in a way that lets them keep pace if not accelerate revenue.
If you are not impacted by economic incentives, you can continue to not care about this transitional state, but most people do.
First you take your Blendtech and "will it blend" your engineers, then upload the result to the cloud inside what is called an S3 bucket (don't forget to set access permissions on your buckets kids!) to be digested by the clankers, sit back and profit!
Dark humor aside I think disconnecting a bunch of problem solvers from their computing equipment could really enhance the world, putting that analytical power into the world in person could move a lot of cogs, rather then marshalling JSON.