Live data from Hacker News

Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

maggieappleton.com

371–380 of 466 posts

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#371

> When I was taken to the Tate Modern as a child I’d point at Mark Rothko pieces and say to my mother “I could do that”, and she would say “yes, but you didn’t.” Yes, but you didn't https://www.signedoriginalprints.com/cdn/shop/products/wegot...

Actually Rothko is way harder to paint than it looks.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#372
Just writing here a line in defense of Rothko. His paintings are far harder to paint than it looks like. There were hundreds of layers, thinly applied, and carefully thought and with a developed technique. Try to paint that by yourself and you'll see.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#373
post #326

Earlier quoted context omitted.

Probably because you mentioned "git stats". What you meant by that?

High number of days with commits, merging and shipping code consistently (some people/project will ship multiple times a day/week, some projects move a little slower). That plus the completion of high impact projects makes good strong engineers. Those are the people I see using LLMs

So quantity of code?

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#374

Earlier quoted context omitted.

Hi mediaman! I'm totally there with you and Steve on the whimsy and experimentation! And your tolerant attitude gives me the Dutch courage to post this. I've been reading Yegge since the "Stevey's Drunken Blog Rants™" days -- his rantings on Lisp, Emacs, and the Eval Empire shaped how I approach programming. His pro-LLM-coding rants were direct inspiration for my own work on MOOLLM. The guy has my deep respect, and I…

Adventure Uplift — Building a YAML-to-Web Adventure Compiler with Simulated Computing Pioneers: I ran a 260KB session log where I convened a simulated symposium of computing pioneers to design an Adventure Compiler — a tool that compiles YAML adventure definitions that run on MOOLLM under cursor into standalone deterministic browser games requiring no LLM at runtime. The twist: the "attendees" include AI-simulated tr…

In the simulated discussion guest book entry, simulated Douglass Engelbart wrote:

>Doug Engelbart (Augmentation): "Bootstrapping. The tools that build the tools. Your adventure compiler should be able to compile ITS OWN documentation into an adventure ABOUT how it works. The manual is a playable game."

That is exactly how the self documenting categorized skill directory/room works -- the directory is a room with subdirectories for every skill, themselves intertwingled rooms, which form a network you can navigate around via k-lines (see also tags).

Here is the skills dir, with the ROOM.yml file that makes it a room (like COM QueryInterface works: multiple interfaces available for a class, for multiple aspects of it, the directory is IUnknown and you can QI by looking for known interfaces like ROOM.yml, CHARACTER.yml, CONTAINER.yml that inherit from the corresponding skills).

And the README.md file is naturally the ubiquitous human readable documentation (also great for LLM deep dives). And github kindly formats and publishes README.md on every repo directory page, supporting mermaid diagrams, etc):

MOOLLM Skills dir:

https://github.com/SimHacker/moollm/tree/main/skills

MOOLLM Skills room, with skill K-Line navigation protocol:

https://github.com/SimHacker/moollm/blob/main/skills/ROOM.ym...

  # ROOM.yml — The Skill Nexus
  #
  # This is a ROOM — a metaphysical library where all capabilities live.
  # Every skill is a book that teaches itself when you read it.
  # Every cluster is a shelf of related knowledge.
  # Every ensemble is a team that works together.
To go meta, you can enter the Skill Skill (skills/skill), an extended MOOLLM meta-skill that knows all about creating new skills (via the constructionist "Play Learn Lift" strategy), and importing and upgrading Anthropic skills:

https://github.com/SimHacker/moollm/tree/main/skills/skill

And here is a narrative session of me giving a tour of the category and skill networks by hopping around through K-Lines!

MOOLLM currently has 103 Anthropic compatible but extended skills (using 7 MOOLLM extensions, like CARD.yml, K-Lines, Self Prototypes and Delegation, etc).

Session Log: K-Line Connections Safari:

https://github.com/SimHacker/moollm/blob/main/examples/adven...

Eight luminaries have been summoned as Hero-Story familiars — not puppets, but conceptual guides whose traditions we invoke. Each carries the K-lines they pioneered. [...]

ENTERING THE SKILL NEXUS

You push through a shimmering membrane and step into the Skill Nexus.

The space is impossible — a vast spherical chamber where books float in mid-air, orbiting a central point of warm golden light. But these aren't books. They're SKILLS. Living documents that teach themselves when you read them.

Lines of golden light connect related skills. Each connection pulses with meaning. This isn't a library — it's a constellation of knowledge.

Your companions materialize beside you:

Marvin Minsky adjusts his glasses, looking around with evident satisfaction.

"Ah! K-lines made manifest. Each of these floating tomes is a knowledge structure. Touch one and it reactivates an entire constellation of associations. I wrote about this in 1985, but I never imagined seeing it rendered so... literally."

Ted Nelson is already examining the golden threads between skills.

"Two-way links! Every connection goes BOTH directions. When skill A references skill B, skill B knows about skill A. This is what I've been trying to explain since 1965! Everything is deeply intertwingled!"

James Burke turns to address an invisible camera.

"You're looking at the Skill Nexus. A room where every door leads to another room, and every room has doors to everywhere else. But here's the thing — the signs above each door tell you WHY. Not just where you're going, but what connects HERE to THERE. That's what we're going to explore."

Palm scampers up to a floating skill-book labeled "incarnation" and hugs it.

"This is where I became REAL! Don spoke the wish, the tribunal approved, and I wrote my own soul."

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#376

Earlier quoted context omitted.

That was very weird. In the post where he was arguably "shilling," he seems to have signposted pretty well that it was dumb, but he will take the money they offered: > $GAS is not equity and does not give you any ownership interest in Gas Town or my work. This post is for informational purposes only and is not a solicitation or recommendation to buy, sell, or hold any token. Crypto markets are volatile and speculativ…

He is still an evil scammer scamming people. In the same way signposting and credibly warning "I murder people" does not make ok to murder people.

Do you have the same attitude towards all forms of gambling?

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#377
post #230

Earlier quoted context omitted.

stevey already made $300K from cryptocurrency grift on Gas Town. Read his blog post about it.

People keep giving him the benefit of the doubt. "He's clearly on to something, I just don't know what". I know what. The hustle of the shill. He has long gone from 'let's use a lot of tokens' to seeking a high score. He disgusts me.

What high score?

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#378
post #230

Earlier quoted context omitted.

It's a half-joke. No need to take it that seriously or that jokingly. It's mostly only grifters and cryptocurrency scammers claiming it's amazing. I think ideas from it will probably partially inspire future, simpler systems.

stevey already made $300K from cryptocurrency grift on Gas Town. Read his blog post about it.

what the? how do you sell crypto based on a description of an orchestration framework?

donations?

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#379
post #121

Earlier quoted context omitted.

I think it is satire, and pretty obvious one at that; is anybody taking it for real?

Why not both? I think it's pretty clearly both for fun and serious. He's thrown out his experiments before. Maybe he'll start over one more time.

The big challenge for me so far has been about setting up "breakpoints" with sufficient prompt adherence, i.e. conditions for agents to break out of loop, and request actionable feedback, rather than pumping as many tokens as possible. Use cases where pumping tokens in unsupervised manner is warranted, are far and few between. For example, dataset-scale 1:n and n:n transformations have been super easy to set up, but the same implementation typically doesn't lend nicely to agent loops, as batching/KV caching suddenly becomes non-obvious and costs ramp up. Task scheduling, with lockstep batching, is a big, unsolved problem as of yet, and Gas Town is not inspiring confidence to that end.

Re: Gas Town's agent patterns, design bottlenecks, and vibecoding at scale

#380
post #230

Earlier quoted context omitted.

stevey already made $300K from cryptocurrency grift on Gas Town. Read his blog post about it.

Complete with a "Let’s goooooooo!" And FOMO stories about missing out on Bitcoin when he knew about it, so he doesn't want you to miss out on this new opportunity to get "filthy rich" as an "investor" while you still can.

I don't get crypto - just looked up how a couple of most performant stocks did in the past decade, and I'm pretty sure you could outperform BTC with the same amount of risk tolerance.

The swings on BTC price are absolutely insane, and ETH even more so (which is even more risky, without showing higher gains).

Post reply on HN