Kimi K2.5 has arrived! 🥝
630,072 次观看
35 条评论
评论来自 X (Twitter) 上的原帖

@theo
👀
93 个赞

@mervenoyann
huge congrats 🔥
53 个赞

@SimplySigmoid
first clawdbot now kimi no excuses
51 个赞

@peter6759
Agent Swarm looks interesting. Trained with Parallel-Agent Reinforcement Learning (PARL), K2.5 learns to self-direct an agent swarm of up to 100 sub-agents, executing parallel workflows across up to 1,500 coordinated steps, without predefined roles or hand-crafted workflows. PARL uses a trainable orchestrator agent to decompose tasks into parallelizable subtasks, each executed by dynamically instantiated, frozen subagents. Running these subtasks concurrently significantly reduces end-to-end latency compared to sequential agent execution.
50 个赞

@SimplySigmoid
still cannot reach nano nanana pr
18 个赞

@pixincreate
does it support ralph? harness? toolcalling? and all other modern buzzwords??? kind of excited to run it locally.
12 个赞

@ShengyuanS
I was vibe testing K2.5 for this video earlier this week, and I’d never seen AI produce interactions like this before. So I used some of Kimi’s own creations as transitions in it.
12 个赞

@ContextrixAi
Kimi K2.5 dropping with Aesthetic Coding and Agent Swarm is exciting.
10 个赞

@wangwei1237
How to understand the concept of the "Agent Swarm"?
10 个赞

@yacinekhoualdi
Kimi k2.5 has arrived
8 个赞

@daniel_nguyenx
Hi team. I can't seem to get the built-in web_search tool to work with the Kimi K2.5 model. Can someone take a look? It works with Kimi K2 thinking & kimi-k2 preview models.
6 个赞

@vectro
Agent swarm looks promising
3 个赞

@Mawzeeeee
ok but can it center a div?
3 个赞

@chocolateyai1
The AI agent era!
3 个赞

@LinusEkenstam
Kimchi?
3 个赞

@gradientintern
niu
3 个赞

@dikang_du
Unleash the Swarm. 🐝
3 个赞

@subhajitlucky
Did you make it using Skills?
2 个赞

@hyva21
Huge thanks to the whole crew behind Kimi K2.5 crushing the drop!
2 个赞

@amos_gyamfi
Well done. I am interested in testing its visual understanding, integrating it with I will share a demo soon.
2 个赞














