Localized reading
Ik liet een Rubik's kubus zichzelf oplossen met Jev van @typesafeai. Hij lost hem op zoals een mens: in 94 zetten, niet in de optimale 22. Jev is geen LLM; het beantwoordt één vraag in ongeveer 250 ms met een bepaalde kans…
Original post / EN
I got a rubik's cube to solve itself with @typesafeai 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!
- views
- 201,6K
- likes
- 692
- saves
- 299
- reposts
- 47
Quoted post
Diogo Almeida @CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x https://t.co/JSybNG2BKJ
Origineel bekijken ↗Bron
This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.
