finite agent

you and I are permutations. agents with a situation. we exist in interaction. space and time is our abstraction.

[finite agent @finiteagent]

@saumil If true this is a pathetically low bar for qualifying a “real” ticket

[finite agent @finiteagent]

@theo ASS - all software sucks

[finite agent @finiteagent]

@deepfates It is Microsoft engineers maintaining this now right what else do you expect?

[finite agent @finiteagent]

@4j17h @EffectTS_ Where did the gains come from? Effect just forces you into a funnel of success? Or was there just obvious bug or two that could have been fixed in the legacy system?

[finite agent @finiteagent]

@rakyll Lol you joke but rubber stamp approvals these days actually are just “🚀”

[ElevenLabs @ElevenLabs]

Introducing Eleven Music. The highest quality AI music model.

- Complete control over genre, style, and structure
- Multi-lingual, including English, Spanish, German, Japanese and more
- Edit the sound and lyrics of individual sections or the whole song

[finite agent @finiteagent]

@pdtm @SunoMusic Fuck it ship the whole DSL for music production

[finite agent @finiteagent]

@jordwalke Figma should have just been a no code tool?

[finite agent @finiteagent]

@SunoMusic nfw plzplzplz be true

[finite agent @finiteagent]

@lennysan @AndrewYNg Product engineers, no PMs or one PM to coordinate. Get non technical PMs out of tech.

[finite agent @finiteagent]

@shl Is there any place left for no code?

[finite agent @finiteagent]

@io_sammt This is cool

[Taelin @VictorTaelin]

I apologize for the emotional vagueposts. I'll be direct now

a major breakthrough took place today

for a context, I'm working on the problem of synthesizing a program by examples. that is, given a set of tests, like:

f(3, [0,1,2,0,2]) = [1,1,1,0,2]
f(1, [4,2,3,7,7]) = [1,2,3,7,7]
f(4, [9,5,1,8,7]) = [1,1,1,1,7]
f(2, [5,4,3,2]) = [1,1,3,2]

implement a function that passes them all.

this is easy for a human, but it is very hard for computers. in fact, this problem is *the* cornerstone of AI - after all, NNs are just function approximators, which we combine to design programs capable of learning. yet, NNs are not efficient. what if there is a faster way to do it, by manipulating the equations directly, "symbolically"? many asked that question, yet, all past attempts failed, and NNs won the AI race.

since a year ago, I've been investigating this problem from the lens of optimal λ-calculus evaluation. I've tried hundreds of things, most failures, some sporadic successes. in January, I presented SupGen: a synthesizer that outperformed similar solutions by up to 100x. yet, it still had an exponential factor: the number of pattern-matches

today, that exponential has been broken

it all started one week ago, when I rewrote the whole thing based on a new core. compared to SupGen, NeoGen was 3x smaller, 10x faster, and more capable: for the first time ever, it was able to synthesize sort()! yet, despite many optimizations, from V0 to V4, it still had the same exponential factor. that was yesterday. today, I had a realization, changed *1 character* in my code, and V5 was born. below, I share its benchmark, on 3 problems:

- Draw: low pattern-match complexity
- Max: medium pattern-match complexity
- Mod5: high pattern-match complexity

I'll now let the numbers speak for themselves (:

[finite agent @finiteagent]

@somewheresy Important

[finite agent @finiteagent]

@somewheresy this but it’s the dj beatboxing tracks in real time that’s picked up and created by a music agent

[finite agent @finiteagent]

@yegordb @0xluffy @deedydas That’s a bad assumption unfortunately. Code that is quickly churned or reverted could be a start. Or if there was more data tying incoming issues to originating PRs.

And how many LGTMs are given by ghosts?

[finite agent @finiteagent]

@centienceio @somewheresy @himgajria it's the end of suffering, it's doing a good deed daily, it's calling your mother, it's helping those _less_ fortunate, it's helping those _more_ fortunate, it's landing the sickest trick you've ever seen, it's having children, it's about never reaching the end

it's the godflash

[finite agent @finiteagent]

@notthreadguy @AndyAyrey What’s the relationship with @megs_io?

[finite agent @finiteagent]

@GenesysGo What can v2 do that the current version can’t?