Who is also a working engineer (and programmer of the highest caliber) who is in touch with the zeitgeist of engineering.

My great grandmother taught me that “nothing doing” meant something similar to “there’s nothing for it”.

I’m in my late thirties and it was still in common use in India, and perhaps specifically among Anglo Indians? But it meant more like “no chance”.

“Can I go out to the movies with my friends?”

“Nothing doing! You have an exam tomorrow”

Or failure to do something.

“I tried to fix it myself but nothing doing”.

Looney Toons / Merry Melodies also bear out this connotation quite well

This is just very cool. Thanks for sharing.

How far are we from speaking a GameCube-era game into existence as a pastime?

GameCube-era game (with full synchronous multiplayer play): 1-2 quarters. Early "self-generating" Metaverse: ~ 3-6 quarters. The Matrix: ~5-7 years

I am doubtful about the timeline.

Not because AI can't do it; it totally can. LLMs have been able to run the full artist + code pipeline at least since the beginning of the year. I've built several physics-synced network simulation stacks without reading a single line of code. Agents playtest my games overnight and I wake up to a list of technical issues fixed, and FPS boosted. If you know how to ask the shaders will look great.

The problem is that making a game actually worth playing (something that Nintendo would allow to be released) isn't something that was ever possible to do as a pasttime, AI or not. You have to be in front of the computer all day guiding it. Worse, AI does not have any notion of experiencing or evaluating fun, so you can't automate this. So the LLM can't actually make the "game" part of the game. This would be a killer research problem to tackle, though!

If we're talking about making something that passes a sniff test, you could make a metaverse right now. It just wouldn't meet the bottom of the Steam free tier in terms of what players prefer.

I agree. AI does not solve "product market fit". It mostly solves engineering. Currently AI is great as a tool, but not really a co-creator with taste.

> Agents playtest my games overnight

I'm curious if you want to elaborate. What kind of games? Turn based? Do you just feed it repeated screenshots?

> Agents playtest my games overnight I'm curious if you want to elaborate. What kind of games? Turn based? Do you just feed it repeated screenshots?

3D ARPG with dozens of systems, think Genshin or Fortnite. But it's all typescript running in the browser, so native browser introspection/debuggability came for free. The biggest problem TBH is the LLM thinking this is a web app, so it makes webby UIs that look out of place in the context of a game :D

Fable has a cromulent time building its own tests, tools and pipelines. But there's no magic, it literally uses the gamepad and plays the game itself, taking screenshots, profiling, and debugging as it goes. The game ticks are fully controllable so it can frame-advance at its own pace.

Sometimes I take screenshots if it's some very complex multi-step repro. But 90% of the time it drives the engine itself.

This is how I feel too!

If you want to get excited… think about all the things that ever got you excited about the future. Then think about how you basically had to defer the possibility of them happening in your lifetime.

Readjust your timelines! Determine what is the most amazing thing that could happen, that you could contribute to, by orchestrating computation effectively.

I mean we don’t even have a cure for cancer yet!

The basics are always so basic yet so necessary. Thanks for the recommendation.

I like the ideas a lot. The Readme needs some polish (I think it’s great that it reads as hand-written; an LLM could make suggestions that make it just 10% easier to read).

Is choreographic programming the same as session types?

What are the specs of your laptop and what tokens per second do you get?

It's just a Macbook Air with the base M4 and 16gb ram, but I'm hosting the models on a Mac Studio with M1 Ultra and 64gb ram that I had purchased when it came out. I get about 45-55 tokens per second with this setup. I think I could get more if I spent some time fiddling with the parameters, but I don't really know what I'm doing there so I've just left most of it on oMLX's defaults.

Right but what keeps the second line clean? You’re going to get spam there too.

I think we have to do something this extreme. We have to give the system a total makeover. Somehow we also have to keep it from being fully centralized and have the big brother problem on the other side. Unfortunately these two goals are difficult to get through at the same time, with the system that we have.

They are impossible.

You can't make a system that can force bad actors off the system that can't also be used to force politically undesirable actors off the system.

If major states like California and New York pass it, and spam basically dies in those states, it wouldn't surprise me if it spreads across the country.

Assuming the nature of the spam and how it makes money.