你可能會喜歡
More and more it seems artificial intelligence differs from human intelligence. Hinton noted how you can perfectly clone and distribute learning. Not to mention the ability to merge models and blocks. A new and very interesting paradigm is very large context lengths.
∇f 已轉發
Sora from OpenAI and Gemini 1.5 from Google are both super impressive. Both rely on long context transformers. I think the lesson is that semi parametric models are great - condition on all past data, whether real or self generated, just like a good Bayesian :)
LMs are trained under so much ambiguity. It's remarkable what they learn to work with
It's amazing how much more intelligent models become when trained over longer contexts
United States 趨勢
- 1. #GrandEgyptianMuseum 24.3K posts
- 2. #GEM𓅓 7,010 posts
- 3. #Talus_Labs N/A
- 4. Game 7 74.5K posts
- 5. jungkook 812K posts
- 6. #capcutai N/A
- 7. Happy New Month 147K posts
- 8. Kawhi 7,765 posts
- 9. Ja Morant 5,520 posts
- 10. Glasnow 6,685 posts
- 11. Barger 6,041 posts
- 12. vmin 3,787 posts
- 13. Grizzlies 7,330 posts
- 14. Bulls 31.9K posts
- 15. Halloween 2025 206K posts
- 16. #RipCity N/A
- 17. Justin Dean 2,514 posts
- 18. Roki 7,780 posts
- 19. Sasaki 11.2K posts
- 20. Rojas 11.4K posts
你可能會喜歡
-
Yash Kant
@yash2kant -
mike
@ParlayTrader -
Robert Vacareanu
@robert_nlp -
Paul Thayer
@ProjectNaosis -
andreas
@ndreaslarsen -
518420.bnb
@realmanhhung -
Greg ⏹️ Colbourn
@gcolbourn -
DXN
@dan_xu_na -
Vaishaal Shankar
@Vaishaal -
Barkatul Mujauddin
@barkatul_twt -
🖌️Poonam Jha | art-a-tech 🪈
@poonmjha -
Ekdeep Singh
@EkdeepL -
jeffsupreme
@yesshefjef -
Brian Reynolds
@breynoldz -
Brendan McCaughey ✍️🎥🎞️🎬
@multitude27
Loading...
Something went wrong.
Something went wrong.