osmarks/documentation
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Edit ‘good_ideas’: Synced 1731013539906

Browse Source
This commit is contained in:
sync 2024-11-07 21:20:42 +00:00 committed by wikimind
parent a3b5d73d67
commit b650b9806c
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
good_ideas.myco
View File

@ -13,6 +13,7 @@ Meme sparse autoencoding (I think a CLIP SAE already exists though).
Similarly, contrastive RL for computer algebra (specifically, proving that expressions equal other expressions via making substitutions repeatedly). Try and contrastively learn a "how close is this expression to this other one" function (I think with an action input?). Bootstrap to progressively harder problems. Similarly, contrastive RL for computer algebra (specifically, proving that expressions equal other expressions via making substitutions repeatedly). Try and contrastively learn a "how close is this expression to this other one" function (I think with an action input?). Bootstrap to progressively harder problems.
* What does Gyges mean by "anyone who wants it: you should be able to train contrastive models way faster if you use lsh to determine pairs to contrast"? This might contain alpha. * What does Gyges mean by "anyone who wants it: you should be able to train contrastive models way faster if you use lsh to determine pairs to contrast"? This might contain alpha.
* Maybe this should be a "theorem prover" and not an "expression rewriter". I think they're fairly similar anyway. * Maybe this should be a "theorem prover" and not an "expression rewriter". I think they're fairly similar anyway.
* Check sticky note for slightly more detailed sketch.
} }
* { * {
Startup ideas: Startup ideas:
@ -61,3 +62,12 @@ https://worksinprogress.co/issue/the-beauty-of-concrete/
* AutoGaryMarcus. * AutoGaryMarcus.
* Automate those one-way/recorded video interviews using an LLM, TTS and deepfake system. * Automate those one-way/recorded video interviews using an LLM, TTS and deepfake system.
* Hex-grid particle simulator (similar to the Powder Toy) with GPU acceleration or HashLife algorithm. * Hex-grid particle simulator (similar to the Powder Toy) with GPU acceleration or HashLife algorithm.
* Fix https://arxiv.org/abs/2411.00566 with less deranged ML.
* {
Diffusion model for Minecraft worlds.
* Scrape the internet for worlds, extract "interesting" regions.
* How to deal with the large volume of data in a world? 16³ is big. Probably more compressible than 2D though. Apply HDiT (?).
}
* Autonomous, rogue [[Autogollark]].
* Make a high-performance physically plausible space combat simulator and do RL to spite Devon Eriksen.
* Simulate self-consistent time travel in games by having absurdly superhuman AI player enforce consistency using "random" degrees of freedom.