Zephry
58 posts

Zephry
@Anton_Kopaev
Интроверт, жадина
Чита, Забайкальский край Katılım Mayıs 2021
32 Takip Edilen37 Takipçiler

WOW
So K3 is performing immensely well on the serious private evals too
Datacurve@datacurve
Kimi K3 debuts at #3 on DeepSWE. It's the first open-weights model that delivers frontier-level performance, achieving results similar to Claude Fable and GPT-5.6 Sol.
English

Kimi K3 and GLM 5.2 are remarkable in that these labs *underreport* their model's performance on the most valuable evals in official announcements. In DeepSWE, K3 is not 2.5% behind Fable. More like 1%. And cheaper.
We're a long way from "benchmaxxing" era. Update accordingly.


Datacurve@datacurve
Kimi K3 debuts at #3 on DeepSWE. It's the first open-weights model that delivers frontier-level performance, achieving results similar to Claude Fable and GPT-5.6 Sol.
English

@mark_k but quite the opposite, i'd say kimi is every bit as much a true believer in scaling laws as A\, arguably more so than oai
English

"PCs will have 4TB+ of Flash storage with ultra high bandwidth"
NAND bull Tim Sweeney
Tim Sweeney@TimSweeneyEpic
One element of the strange climate now is the scale and inaccessibility of data centers versus PCs. But post-memory-disruption, PCs will have 4TB+ of Flash storage with ultra high bandwidth and we'll just run these models locally and see they're no big deal.
English
Zephry retweetledi
Zephry retweetledi
Zephry retweetledi

A cozy weekday dinner: warm tomato soup + crispy garlic bread Perfect for slow evenings at home. #SimpleEats,

English
Zephry retweetledi

















