thomasfromcdnjs

I think that the generative ui and self evolving databases per user is definitely coming, I think they are making this wager too. A lot of pieces of the ecosystem haven't been thought out fully yet and there is a shift in user experience e.g. a lot of people are more content with just using Dots then loading up apps and visuals, when they can just read what they needed to know.

Yeah, I suggested to take down the app someone between seeing the Gina (core) comment (saying php.ini etc changes won't do anything) and after seeing the Cloudflare CTO tweet.

That is a great suggestion, and you are correct, so I will do what you said!

I've been vibe coding my own language and it's compiler is in Haskell, it's been great for the agents to be inspired by Haskell and I'm having fun just adding random language features, currently implementing prophecy ghost variables. Not really a public project but can suss it out for now at http://lsalpha.com

have a fair idea of the criticisms, but being playful I decided to have a bit of an open mind see if the idea has legs. I don't know shit about hardware, not much about compilation and I've got self purported decent level of understanding of the nature of LLM's. If you click around there are 4kb binary outputs that work, the generation is using my 6-luna api credits so I might have to drop it depending if people are interested. Experiments with lesser models are a bit meh and I'm of the mind that the open weight efforts are still behind (I do think they will catch up for weird problems like this)

The next problem to work on in this scenario, is modules, give the LLM instructions to write orchestration of the outputs, given that they can only probably write 8kb of binaries without losing their fucking mind. (this could be wrong too)

Going to setup a shared community of hosted libraries and work towards an operating system, forgive the buzz words, but might use something like Jev to help with finding compatible binary artefacts.

---

The virtual cpu design is written in typescript, it has a terminal with keyboard inputs, and a framebuffer for rendering.

All generations are public at the moment, so you can browse and share, best I've got is a little mario world, use your imagination.

---

The proposed instruction set is named "ANMA-1", I'd recommend clicking the "System prompt" button in the top bar.

I have a fair idea of the criticisms, but being playful I decided to have a bit of an open mind see if the idea has legs. I don't know shit about hardware, not much about compilation and I've got self purported decent level of understanding of the nature of LLM's.

If you click around there are 4kb binary outputs that work, the generation is using my 6-luna api credits so I might have to drop it depending if people are interested. Experiments with lesser models are a bit meh and I'm of the mind that the open weight efforts are still behind (I do think they will catch up for weird problems like this)

The next problem to work on in this scenario, is modules, give the LLM instructions to write orchestration of the outputs, given that they can only probably write 8kb of binaries without losing their fucking mind. (this could be wrong too)

Going to setup a shared community of hosted libraries and work towards an operating system, forgive the buzz words, but might use something like Jev to help with finding compatible binary artefacts.

---

The virtual cpu design is written in typescript, it has a terminal with keyboard inputs, and a framebuffer for rendering.

All generations are public at the moment, so you can browse and share, best I've got is a little mario world, use your imagination.

---

The proposed instruction set is named "ANMA-1", I'd recommend clicking the "System prompt" button in the top bar.

Confirmed, orbit!

Hell yeah, that was the longest 10 minutes.

aha I appreciate the rant, and you obviously know what you are talking about.

I have used the Lean 4 approach and I wasn't proposing it solves the problem, but it has reduced the search space for me in certain circumstances. At best it's a nice way for agents to keep in their context windows potential relations, I made it create enormous amounts of hypothetical nodes and then visualized it so I could talk with my relatives about potential paths.

As a side note, I believe, if we had a better DNA site that had great API access (and exposed genomes), I think agents could probably solve genealogy, even as far as complex endogamics.

(I don't think centimorgans is that useful past 4 generations kind of thing)

A couple ideas (that I have used with success);

- ask it to generate Lean 4 proofs based off centimorgans

- extract subject, object, subjects from all source texts and create a graph database (maybe someone mentioned a red dog in their oral history, and someone else mentioned a sick dog in a eulogy, ask ai to explore weakly correlated connections, sometimes pays off)

Amen.

I've been doing family history on my aboriginal Australian side, there were a bunch of Lutheran missions, and ever so kindly they digitized 800 pages for me, but it was all written in German. I transcribed and translated all of it.

https://drive.google.com/file/d/1en9gDgZRP7EmSHU72k6g2Iz3RRf...

I sent it back and they didn't acknowledge it, probably for various reasons, and I doubt they would like me linking it above.

Beyond being fascinating in general, I also found that from a different state in Australia there was an aboriginal who became a man of letters came to my ancestral state and was the first to write the language of the tribe, I think (not something easy to prove) it's the first ever written version of the tribal language circa ~1870 of Kuku Yalanji.

While I get the point and it's true.

I'm a little more flexible, if the new knowledge (that human's don't understand) can be put into a mechanism and have an observable effect, I'd be happy enough. e.g. a new type of rocket fuel that burns 1000x more efficiently.

I gave it a spin using muse 1.3

Got it to port kaparthys microgpt -> https://github.com/thomasdavis/bend-experiments/tree/main/mi...

muse did surprisingly well getting it to work, can't speak for the code quality.

Well described the problem scope.

I wonder if harness-hooks + Jev (equivalents) could semantically lint for `sloppy_law` etc when ever they are edited

Beautiful!

Awesome! doing similar things

ssh sshfighter.com

Been optimising an ssh ansi rendering engine for six months, starting to look great. Homepage is slop please forgive

Gen UI is meant to be design agnostic, the output is just the content and the form. It is on the implementation, agentic or human to make it look good.

would love to see what you build. i am working a ssh mmorpg, about to start working on the lore

aha i've been hacking away at the terminal graphics over ssh for ages for months, the repo is fully open source.

the sprites aren't all the same size or as good as they could be but already spent too much $$ on sprites.

the sprites are just passed through algorithms that optimize for what text characters at different aspects would make them look good.

I built sshfighter.com recently and pushed terminal graphics to the limit (with no kity)

You have to zoom out to get more pixels for it to look good (and press v to switch rendering engine if it starts off poor)

> ssh sshfighter.com

And instructions on how to do it are here -> https://github.com/thomasdavis/sshfighter.com/blob/main/docs...

(the homepage is ai generated, the real work is in the ssh server)

Fair criticisms, I didn't even really want a homepage, just let the ssh speak for itself kind of thing.

I have spent quite a bit of time on getting that rendering engine in ssh, I don't think I've ever seen anyone get the quality of graphics on ssh so I thought it was unique.

Will do some more homepage clean up, and try to promote that product is the ssh game, not the homepage.