@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?
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
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 (:
@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?
@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