Localized reading
Conseguí que un cubo de Rubik se resolviera solo usando Jev de @typesafeai. Lo resuelve como lo haría una persona: en 94 movimientos, no con la solución óptima de 22. Jev no es un LLM; solo responde una pregunta en unos 250 ms con una probabilidad. Así que programé el método para principiantes —el que se aprende en YouTube: cruz blanca, esquinas, capa intermedia y capa amarilla— y, en cada paso, Jev observa el cubo y elige en qué situación está. El código comprueba cada elección. Unos 4 segundos de tiempo de modelo. El vídeo está ralentizado para que puedas leerlo.
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
- 201,6 mil
- 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
Ver original ↗Fuente
This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.
