I've always believed that intelligence should come from simple, general building blocks that learn…
@_albertgu27.165 Follower
1.048.892 Aufrufe
16 Kommentare
Kommentare aus dem Originalbeitrag auf X (Twitter)

@_albertgu
Blog: Part 1 Part 2 (Voiceover created entirely by Cartesia's Sonic text-to-speech model!)
67 Likes

@quanathan_zhou
This is the kind of work that makes me excited to be at @cartesia. Huge props to the team behind H-Nets~
6 Likes

@JustinWaugh
So exciting to see h-net results! The In-context tokenization part is so cool - show's the real power of hnet imo. Feels like it's directionarlly a step on the path to a true continuous learner / infinite context.
6 Likes

@karan_bania
so cool to see it work on images and patchify background as one token
2 Likes

@timshi_ai
amazing
1 Like

@nikkuv5787
bitter lesson never misses, we just keep forgetting it every hype cycle
1 Like

@agneau123
Raw bytes still force the hierarchy
1 Like

@hailports
raw data, huh. language already comes pre-chewed by people. the real test is what happens where nobody bothered to name things.
1 Like

@ChangJonathanC
what happened here?

@cmitsakis
the efficiency jump is huge! the bitter lesson is always true

@chirag
Other people have spoken of a cognitive core with search and tools. A lot of the initial wow came from the fact that some x million documents have been consumed and can be recalled verbatim. That's a different task from getting work done.

@AIQuanting
What does staying at the byte level cost you at inference time?

@1rreverant
does any of the insights translate to image/video-gen?

@GravityRsch
10x less compute is absurd

@nancycxu
Incredible work!!

@sophiamyang
beautiful!
