logoalt Hacker News

rgloveryesterday at 12:18 AM3 repliesview on HN

Just tried K3 out for the first time today and it's a legitimate threat.

Temporarily (maybe permanently) using it as my daily driver but it's wild how comparable it is to Opus 4.7/4.8 (what's been my go to for a bit now—wrote a quick post on what I found today [1]).

[1] https://graybearding.bearblog.dev/kimi-k3-is-insane/


Replies

kroatonyesterday at 12:21 AM

Better than Opus 4.8 on complex tasks but tends to overthink. It found a bunch of bugs and architecture issues that only 5.6 Sol Max and Fable on my C++ projects.

ATMLOTTOBEERyesterday at 1:55 AM

Agreed. Dropped my $200/mo Claude I was saturating for the $100/mo moonshot sub and have no complaints

Plus I can actually see the thinking traces and I’m not getting downgraded/denied by anthropic constsntly…

show 1 reply
igraviousyesterday at 7:10 AM

threat?

that's a weird way of describing a near frontier open weights un-crippled useful coding buddy

do you work for OpenAI or Anthropic per chance?

show 1 reply