Want to wade into the snowy surf of the abyss? Have a sneer percolating in your system but not enough time/energy to make a whole post about it? Go forth and be mid: Welcome to the Stubsack, your first port of call for learning fresh Awful youāll near-instantly regret.
Any awful.systems sub may be subsneered in this subthread, techtakes or no.
If your sneer seems higher quality than you thought, feel free to cutānāpaste it into its own post ā thereās no quota for posting and the bar really isnāt that high.
The post Xitter web has spawned soo many āesotericā right wing freaks, but thereās no appropriate sneer-space for them. Iām talking redscare-ish, reality challenged āculture criticsā who write about everything but understand nothing. Iām talking about reply-guys who make the same 6 tweets about the same 3 subjects. Theyāre inescapable at this point, yet I donāt see them mocked (as much as they should be)
Like, there was one dude a while back who insisted that women couldnāt be surgeons because they didnāt believe in the moon or in stars? I think each and every one of these guys is uniquely fucked up and if I canāt escape them, I would love to sneer at them.
(Last substack for 2025 - may 2026 bring better tidings. Credit and/or blame to David Gerard for starting this.)
Steve Yegge has created Gas Town, a mess of Claude Code agents forced to cosplay as a k8s cluster with a Mad Max theme. I canāt think of better sneers than Yeggeās own commentary:
If youāre familiar with the Towers-of-Hanoi problem then you can appreciate the contrast between Yeggeās solution and a standard solution; in general, recursive solutions are fewer than ten lines of code.
For comparison, solving for 20 discs in the famously-slow CPython programming system takes less than a second, with most time spent printing lines to the console. The solution length is exponential in the number of discs, and thatās over one million lines total. At thirty hours, Yeggeās harness solves Hanoi at fewer than ten lines/second! Also I canāt help but notice that he didnāt verify the correctness of the solution; by ārunā he means that he got an LLM to print out a solution-shaped line.
Oh. Oh no.
I donāt think I could come up with a better satire of vibe coding and yet here we fucking are. This comes after several pages of explaining the 3 or 4 different hacks responsible for making the agents actually do something when they start up, which Iām pretty sure could be replaced by bit of actual debugging but nope weāre vibe coding now.
Look, Iāve talked before about how I donāt have a lot of experience with software engineering, and please correct me if Iām wrong. But this doesnāt look like an engineered project. It looks like a pile of piles of random shit that he kept throwing back to Claude code until it looked like it did what he wanted.
Just confirming that none of what is described really approaches engineering.
Thatās horrifying. The whole thing reads like an over-elaborate joke poking fun at vibe-coders.
Itās like someone looked at the javascript ecosystem of tools and libraries and thought that it was great but far too conservative and cautious and excessively engineered. (fwiw, yegge kinda predicted the rise of javascript back in the dayā¦ heās had some good thoughts on the software industry, but I donāt think this latest is one of them)
So now we have some kind of meta-vibe-coding where someone gets to play at being a project manager whilst inventing cutesy names and torching huge sums of moneyā¦ but to what end?
Apart from a āhaha, turns out vide coding isnāt vibe engineeringā (because I suspect that ādesignā and āplanā just mean āwrite more prompts and hope for the bestā) I have to ask again: to what end? what is being accomplished here? Where are the great works of agentic vibe coding? This whole thing just seems like it could have been avoided by giving steve a copy of factorio or something, and still generated as many valuable results.
wait what do you mean āreads likeā
please donāt tell me this is earnest?
Think I have mentioned the story I heard here once, about the guy who wrote a program to find some large prime which he ran on the mainframe over the weekend, using up all the calculation budget his uni department had. And then they confronted him with the end result, and the number the program produced ended in a 2. (He had forgotten to code the -1 step).
This reminded me of that story. (At least in this case it actually produced a viable result (if costly), just with a minor error).
Itās okay, he definitely wants to verify it but actually confirming that this whole disaster pile worked as intended and produced usable code apparently didnāt make the cut.
Also worth noting that in the jargon heās created for this, a āwispā is ephemeral rather than a proper output, so it seems like he may have pulled this solution out of the middle of a running attempt to calculate the solution and assumed that it was absolutely correct despite repeatedly saying throughout his writeup here that thereās no guarantee that any given internal step is the right answer. This guy strikes me as very good at branding but not really much else.
??????????????????
Fantastic bit. I wonder if the Computer History Museum will eventually be able to replicate this as the peak of the āgen-AIā era.