Kimi Linear: An Expressive, Efficient Attention Architecture (2025)

Post by nuancebydefault » Tue, Jul 28, 2026, 8:32 PM UTC

hnfong wrote: post #41

pooyamo wrote: post #20

Does any expert in the field know whether it is really the case that this intelligence we are seeing with frontier models is an "emerging" phenomena, only coming up when the architecture is scaled? Like isn't it weird that the 1 million parameter model with the same architecture can't solve basic puzzles but suddenly the 1 trillion parameter can conjure up counter-examples for the Jacobian conjecture? It's unintuitiv…

> one of the basic tenants of algorithm development was that you can't just brute-force your way towards a solution for some complex problems It's kind of sad that popular CS textbooks often focus on solving precise problems with lowest theoretical complexity bounds while ignoring more practical (but generally applicable) computation techniques. In machine learning they call it "gradient descent", which in older days…

Post by thesiti92 » Tue, Jul 28, 2026, 8:52 PM UTC

Post by whimsicalism » Tue, Jul 28, 2026, 9:31 PM UTC

verdverm wrote: post #34

jlamberts wrote: post #27

Earlier quoted context omitted.

This is actually a well-known phenomenon in ML, called "The Bitter Lesson". > One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with increased computation even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are search and learning. The full essay is worth a read, it's pre…

[flagged]

Post by verdverm » Tue, Jul 28, 2026, 10:55 PM UTC

realitylabs wrote: post #114

verdverm wrote: post #34

Earlier quoted context omitted.

[flagged]

Out of curiousity, I like security just as much as the next guy and ensure that certs are valid, ciphers are fresh, and protocols are mature, but I am also not really concerned with an informational site that runs http being browsed. Would you mind sharing what your concern would be with browsing this content over http?

Post by HDBaseT » Tue, Jul 28, 2026, 10:56 PM UTC

trollbridge wrote: post #100

Barbing wrote: post #97

Earlier quoted context omitted.

> chinese models are less censored Tried spicy geopolitical dispute questions?

Yes, and they aren't a problem. I get tired of people claiming this. Go download Qwen 3.6 and run it yourself and fire away.