Localized reading
Saya membuat kubus Rubik menyelesaikan dirinya sendiri dengan Jev dari @typesafeai. Ia menyelesaikannya seperti manusia: 94 langkah, bukan solusi optimal 22 langkah. Jev bukan LLM; ia hanya menjawab satu pertanyaan dengan probabilitas dalam sekitar 250 ms. Saya memasukkan metode pemula ke dalam kode, sehingga Jev melihat kubus dan memilih keadaannya pada setiap langkah, sementara kode memeriksa pilihan itu. Waktu model sekitar 4 detik. Videonya diperlambat agar bisa dibaca!
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 rb
- 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
Lihat versi asli ↗Sumber
This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.
