You might like
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 reposted
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 Trends
- 1. Carson Beck 12.9K posts
- 2. Ohtani 67.6K posts
- 3. Miami 91.7K posts
- 4. Miami 91.7K posts
- 5. Louisville 20.2K posts
- 6. #SmackDown 47.3K posts
- 7. #BostonBlue 5,906 posts
- 8. Jeff Brohm 1,762 posts
- 9. Malachi Toney 2,356 posts
- 10. George Santos 63.4K posts
- 11. Mario Cristobal N/A
- 12. Chris Bell 1,996 posts
- 13. #OPLive 2,208 posts
- 14. Nebraska 13K posts
- 15. Geno 9,303 posts
- 16. 4 INTs N/A
- 17. The U 567K posts
- 18. Raiola 2,304 posts
- 19. Ilja 19.2K posts
- 20. Minnesota 46.4K posts
You might like
-
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.