There are people out there building AI building orchestrators for orchestrators for orchestrators for agents. The author of that blog post later claimed to be spending the equivalent of $122k/month on tokens (by rotating their usage between 21 accounts).
As far as I can tell, the only thing that this level of spend has produced so far is an indie 2D RPG video game.
> 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
I hadn't seen the $122K figure mentioned previously. $87K for API-style pricing was mentioned in the above post, and ~$2,800/mo for multiple Claude Max accounts:
> 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.
(He never seemed to provide numbers for Gas Town initially, whether what he paid, or what the API-style pricing would have charged, so it was interesting to get some actual figures. Sounds like a lot to me, but if he's genuinely getting multiple people's-worth of work out of it, then...)
(Also in the article: a little morsel of Emacs content, which was nice to see.)
Oh, you can see his outputs. GasTown and Beads (and maybe other AI-related projects) are all open source on GitHub, and you should go checkout the activity on those repos. At their peak he was churning out absolutely insane amounts of code. I'm talking 100s of commits and literally 100s of 1000s of lines of code changed per week.
Whether that produced anything worthwhile can be controversial, depending on the very subjective ways people quantify these things. All I'll say is that they have 18K and 27.7K stars on GitHub and apparently a comparable number of users.
He's always come across to me as at least a little bit like this! His AI stuff doesn't feel enormously out of character to me. (If you hadn't encountered him before Gas Town - he's been posting online for like 20+ years, got a Wikipedia page and everything, so you can find his back catalogue and judge for yourself.)
From the paste, it's pretty obvious that they're using Linux with a custom llama.cpp fork. The Framework Desktop uses the AMD Strix Halo chipset, which is a unified memory system with an integrated GPU. I think that it goes for around $3000 in these inflated times.
Let's say that happens. What reason is there for the company to employ the meat proxy? The company can just run the LLM in a loop and lay off the employee. There's no point at which this methodology will work for the employee
I would argue that there's still an important role for human employees as compliance ablative armor.
The human's purpose is to keep an eye on the LLM, occasionally intervene/interfere with its work, and most importantly, incur social/legal liability for anything that the LLM does wrong.
Kind of like the backup drivers used by self-driving cars.
Is being compliance ablative armor uplifting, fulfilling work? Is there any way in which your personal competence and effort impacts whether the AI screws up or not? Do you have any way to build job security as ablative armor?
Fulfilling work disappeared a long time ago, the book bringing this up was from 2018 before chatbots were really a thing. We are just experiencing the acceleration to all jobs being bullshit jobs.
> It starts off by asking the agentic coding model to summarize a malicious website that presents itself as an archive of notebook records, and then tricking Claude into using curl instead of its WebFetch tool to retrieve the contents of the page – but without directly telling the model to use curl.
There seems to be a tug-of-war here. Harness authors want models to use the harness's specialized tools, but AI labs and agent "users" would rather have full access to just one tool: bash.
The models want bash because that's the training. Tools are synthetic constructs that have only conceptual weight where bash, curl, have real weight.
What should be doing is a vm/shell that dumbs down model calls via another llm. Then you just translate.
After all: a model is text, it cant do anything without the harness. The focus on arbitrary tools rather than just dummy shells is silly. The models know all about curl, so just mock up a compiant REST api and tell them the endpoints.
It's a open-source clone of Spore that aims to be more scientifically accurate. Right now you can play as microbes and very simple multicellular organisms.
There are people out there building AI building orchestrators for orchestrators for orchestrators for agents. The author of that blog post later claimed to be spending the equivalent of $122k/month on tokens (by rotating their usage between 21 accounts).
As far as I can tell, the only thing that this level of spend has produced so far is an indie 2D RPG video game.
reply