Coding Agents Will Work All Night While You Sleep: Inside the Continuous Thunderdome
The Shape of Things to Come
Steve Yegge explains how to build a 'loop and graph' system that lets coding agents work through the night on massive problems. He introduces Beads, an issue tracker and knowledge graph, and describes his new harness, Wheelhouse, built for his game Wyvern. Yegge predicts the death of CI/CD and human code review, and discusses the 'Wish Factory' and model welfare. He shares his method of using multiple Claude Max accounts to create an 'infinite token tap'.
Harnesses need to be part of your application, chemically bonded in.
- xnorswap
I don't like using the term "AI psychosis" because it originally meant a narrow definition resulting in genuine psychosis and acute mental health trauma, but seems to have widened to anyone falling down a much wider trapdoor of AI engagement.
But I read, or at least attempt to read, something like this, and I can't help but marvel at the capture that AI agents seem to have on some individuals.
I expected Yegge to, at some point, assuming this isn't still all satire, to take a step back and take stock that the basic harness are improving faster than the rate at which these complex beasts can adjust.
But the opposite has happened, he's dived fully into believing that the secret to unlocking the power of AI is to wrap more layers of AI around it.
If you actually want a problem worked on all night, just fire up fable, type /goal and then describe the goal. With permissive run settings it'll crunch for as long as it needs.
I've not seen any evidence that wrapping that in a further 3 or 4 layers of agents improves anything.
- themgt
Gas Town was intended to be reusable, but I only ever wound up using it to build itself. Gas Town fell apart at the seams with Opus 4.7. Up through 4.6 it was working brilliantly. With 4.7 we saw the introduction of the "just two more things" tic, which prevented Opus from ever converging on being ready to do real work—it always wanted to fiddle with Gas Town itself. The Opus tic never went away, so Gas Town effectively burned down. It had other problems, too, but 4.7 was the final straw.
"True Gas Town has never been tried" etc.
With Wheelhouse, I have reinvented something strangely Gas Town shaped from first principles, but it's running many more agents, and they are far more organized. This has shown me the shape of the changes coming next year. I'm operating about 12 months in the future. I managed this only through luck: for the past 18 months I have had the magic trio of time, money, and energy, and I've been spending it all on figuring this stuff out. And I am grateful for the privilege.
I'm still half-convinced this is Yegge's version of Andy Kaufman's professional wrestling career, "Gas Wheeltown was an 18 month long sociological experiment conducted by Thiel University. The study is now complete, thank you for your time."
- bambax
I used to like Steve's posts. They were all way too long, but a fun and interesting read nonetheless. He started to lose me when at Sourcegraph where he oversell Cody which didn't do anything useful (I even had a commercial meeting with Sourcegraph people who weren't of much help); then he completely lost me with his GasTown business where AI meets crypto (what could possibly go wrong with that). Now I can't read anything from him anymore ;-(
- pringk02
> But my Wyvern development has been burning the equivalent of $87k/month of API token burn, or about 69 billion tokens in July (96% cache hits, fortunately). So I do have to worry about it. I don't care how much money you have; your spouse is not going to let you spend almost ninety thousand dollars a month on your hobby game. I didn't even bother asking.
> My solution has been to create a token tap on $200 Max accounts, which for me work out to ~30x the list-price equivalent. So in reality I'm only spending about $2800/month out of pocket for my $87k "worth" of tokens. Though that number keeps growing alarmingly.
But how much does the game bring in?
- rubzah
I smell an architecture astronaut getting high on abstractions. Taken far enough, it starts to look like psychedelic ramblings of a manic schizophrenic losing grip on reality.
Interestingly, the author actually has a product, something usually missing in claims of the new LLM powered productivity nirvana. Hopefully, with time, there will be a way to verify the effectiveness of all of this fire and fury, measured in actual worthwhile deliveries of this product.