On Kimi K3: Its Capabilities And Related Discontents

·Don't Worry About the Vase··

Kimi K3 is a very good model with excellent benchmarks. Assuming its weights are released as planned it will become, purely in terms of raw capability, the strongest open model.Do not get carried away. Do not judge Kimi K3 only its relative strengths. In aggregate it is several months behind the closed model frontier, at least four and my median guess is six, with the post-training closer and the pre-training farther out. This is less months than before, but the months are denser now. It is some...

Read full article →

Related Articles

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 2mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 2mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 2mo ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 2mo ago
ProgramBench: Can language models rebuild programs from scratch?
jonbaer · Hacker News · 2mo ago