Viewing profile — swax

Yea, I'm working on a open source distributed, self-hosted agent runner https://naisys.org/ I also did a private decentralized system that was like WASTE+DHT around 2009 ( https://…

I did a client called Gnucleus back in the day, the original website is still up at https://gnucleus.org/ I also designed GWebCache with a friend in college (also the IRC caching b…

I’ve been using the same OneNote for like 20 years now. It is backed up, synced and available no matter what device I’m on. Hundreds of lists, notes, references, thoughts, all full…

It's an unsettling feeling as what's more complicated - all the atoms and galaxies, trillions of life forms, the unimaginable distances of our universe OR a relatively simple world…

Sure, so you tell the model, here's a command prompt, what do you type next? Ideally, it types commands, but a lesser model may just type what it's thinking which is invalid. You c…

Yea a lot of this is experimental, I basically have plain text instructions per agent all talking to each other, coordinating and running an entire pipeline to do what would typica…

Throwing this out there, I have a command line driver for LLMs. Lots of little tricks in there to adapt the CLI to make it amiable for LLMs. Like interrupting a long running proces…

Put in the categories, themes, styles you care about, and WallTrek will auto-generate wallpapers for you. Always a nice surprise to see what it comes up with next. Open source, use…

Thanks for trying it. If you click near the edge you should be able to drag it somewhere else.

A small dumb app that allows changing the volume quickly from the taskbar in a single click. Not super interesting, but maybe practically useful for you guys. I made it pretty fast…

I'm working on a Sketch Comedy Database website: https://www.sketchtv.lol/ https://github.com/swax/SCDB Just a fun little CRUD app built with Next.js, MUI, Prisma Postgres. I'm add…

AI advancement is coming at us both ways - orders of magnitude more compute, with orders of magnitude more efficiency. Hyper exponential.

There isn't anywhere on the web the catalogs individual sketches and links them together so hoping to build it out with others who enjoy sketch comedy. Just a fun side project buil…

I mean we have contexts now so large it dwarfs human short term memory right? And then in terms of reading a book, a model's training could be updated with the book, right?

Humans are also trained on what they’ve ‘seen’. What else is there? Idk if humans actually come up with ‘new’ ideas or just hallucinate on what they’ve experienced in combination w…

Opus seems to be much better at that. Probably why it’s so much more expensive. AI companies have to balance costs. I wonder if the public has even seen the most powerful, full fid…

And you just know people will create AI to do that deliberately anyway.

Sometimes I'll tell two agents very explicitly to share the work, "you work on this, the other should work on that." And one of the agents ends up delegating all their work to the …

Yea, there's some logs here https://test.naisys.org/logs/ Inter-agent tasks is a fun one. Sometimes it works out, but a lot of the time they just end up going back and forth talkin…

The step changes in autonomy are very obvious and significant from gpt-3, -4, and to Opus. From my point of view given the kinds of dumb mistakes it makes, it's really just a matte…

I have an open source project that is basically that ( https://naisys.org/ ). From my testing it feels like AI is pretty close as it is to acting autonomously. Opus is noticeably m…

I tried building a MUD with GPT-4 and Claude 3 Opus. They were able to give me the initial setup no problem, but iterating on it was a disaster. This article goes over my experienc…

I've been working on something similar, here's one of their same tests where the AI learns how to make a hidden text image. https://www.youtube.com/watch?v=dHlv7Jl3SFI The real pro…

Amalgamating the pieces is the test. LLMs really can't do it that well. Is it context size, training, number of iterations, number of agents? That's what's being tried to improve t…