Fences, Not Sandboxes

CoolestBeans

What is the overhead to have agents play model UN? Why is the coordination so elaborate? It sounds like a deeply complex and expensive emergent behavior that maybe looks comprehensible but could be nonsensical. Also like any complex system, can you actually predict the outcomes? Waste is a failure case. How do we know the code factory is actually productive or just agents filling up the computation resource cap because they can?

coder-pm

How do you find the bad decisions with so many subscriptions active? isn't that looking for needle in a haystack:)?

mccoyb

> I am running an organization of around 50-60 agents, five of whom are interfacing with around 10 humans in the outside world: myself, my 5-person core game design team, my accountant, my chief of staff, and a few others. Only Fable is allowed to talk to humans, via Slack and email. RIP to those poor humans. I can't imagine having your brain melted by Fablespeak as your FTJ.

nepthar

(Asking sincerely in good faith - I read this note along with skimming a few of the linked ones, and I'm familiar with gastown) Can someone explain the value calculation to me? This seems like someone has truly let AI VASTLY expand the codebase of what seems to be a medium sized hobby game to ~10-100x the amount of engineering required. Especially with statements about how wheelhouse, his software factory, has grown to nearly the size of the actual software he's writing. He also mentions several times that wheelhouse is specific to developing the game. Then, he discusses "pulling in beads" which itself seems on my read to be enormously engineered. (note that he also says that you burn a lot of tokens with agents "keeping your beads in sync" and I didn't have the time to figure out what that meant, but it looks like as complicated as it is, beads can't reconcile itself without burning $$$). It seems like if you answer "yes" at every time you have the question of "can I make AI do this", you end up burning $120k/month in tokens on your side project. Again, I am not disparaging this- but I feel like I am genuinely missing something and would welcome help understanding it.

BeetleB

> I didn't want this to be a long post, and I think I've succeeded. Classic Steve Yegge!

grebc

Yegge’s writing has declined proportionately to his AI usage.

xnx

> First, my secret: I see the future by living in it. I am spending the equivalent of $122k/month of API token spend, or about $4,000 per day, using 21 Claude Max accounts, a number that has been growing steadily at 2 per week. Good to know that together, Yegge and Zitron bring balance to the force.

sneilan1

I'm glad someone is trying this and exploring what's possible. It's easy to deride his work by saying what's the value but are you running 50 fable agents and letting them run wild to see what the future looks like?

jshaqaw

The proof is (or isn't) in the game. If the game is something genuinely great then this all worked and is important. If the game is a bloviated, boring, and derivative mess then it didn't. Without any proof point on the output it is hard to say if the article has any value.

Avshalom

>This tier, or the one just after it, will power hundreds to thousands of new AI employees at every company. >And companies are in no way, shape, or form prepared for this transition. so, uh, what's the business model here?

AgentOrange1234

"Wheelhouse is about 600k lines of code and tests (mostly bash)" This article is a joke right? Please tell me you are joking. Jesus christ.

groby_b

"I would guess I'm one of a handful of top individuals on Earth outside the frontier labs, in terms of my experience with top-end models." I'd argue that number of tokens burned does not translate into "experience". And if you needed to spend $300k or so to find out that process helps manage larger efforts (process is what "fences" are outside Yegge-land), you sure spent a lot. I mean, I'm glad the guy's got a a hobby he enjoys, but there's less insight than you'd hope for.

kibwen

In the glorious future where I can conjure a game with a snap of my fingers for the cost of a pack of gum, why would I ever choose to play Wyvern, the game tailored to Steve Yegge's tastes, when I could just make a game tailored to my tastes? Perhaps Steve will be content to play his MUD with agents pretending to be human players?

nzoschke

Seems like this is the year of the sandbox and governance layers. I recently wrote how we set all this up for our agent computers that help people with their email: https://housecat.com/blog/agent-computer-101 I do agree even more rules help keep things on track, but I do these as linters, specifically as Golang `go vet` and `go fix` commands. That works 100x better than any SKILL.md or team of agents in my experience.

Theory5

I don't even like the idea of humans operating without guardrails where I work, much less AI.

fwlr

> the subject matter is too complicated to explain … All I can do is walk you around like an excited tour guide, one who has unearthed an ancient alien civilization. Now this is AI psychosis.

perrygeo

> So it's not $120k/month of real money, but it's still crazy spend. I would guess I'm one of a handful of top individuals on Earth outside the frontier labs, in terms of my experience with top-end models. We get it bro, you buy lots of tokens. My son buys lots of pokemon cards. Still haven't seen shit for return on that investment either, but as long as its all in good fun, "you do you". > That's how I'm able to tell the future. I'm living in a world that will not become cost-effective for most people for another year. That's pretty easy to verify. #remindme August 24, 2027 - are $120k worth of tokens in 2026 generally "affordable" by 2027? By what mechanism have the economics shifted?

throwaw12

I think Steve somewhat predicted the future well. He might be slightly off, because he is overly optimistic and operates at the edge, but look at Gas Town, when it was released it felt like dystopian, today it looks not too far away, I am sure most of your orgs are already running some kind of agent to triage the tickets and in some cases automatically open the PR in your git repo. I think he is onto something this time as well

AWebOfBrown

I honestly think Yegge has reached a point where he knows he isn't interested in doing the leg work of today's software engineering, but wants his career to ride the wave. The lowest effort, maximum value to extract in his position is abusing the crap out LLMs to an extent that is genuinely novel to secure thought leadership, but on close inspection it's just pointless token spend driving blog posts and publicity. To me it is absolutely farcical that he was being being paid by a harness company (Amp) as a staff software engineer, slop-coded a solution to keeping LLMs on track (Beads), and having paid for all of this Amp and Steve...parted ways. Beads never went into Amp. Someone cottoned on to the value Steve was providing, for my money.

zbentley

Congratulations, you have reinvented RFCs, architecture reviews, linters, and integration tests. From first principles. With cutesy names.