Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
Official3
kimi.com2026-04-20officialauthorityHN front pageabout the Kimi K2 familyHN 710 pts · 372 comments2,299 words
Kimi K2.6 is an open-source model released for advanced coding, long-horizon execution, and agent swarm capabilities. It is available via Kimi.com, the Kimi App, the API, and Kimi Code, showing a 12% increase in code generation accuracy and a 96.60% tool invocation success rate. The model scales agent swarms to 300 sub-agents executing across 4,000 coordinated steps simultaneously.written, reviewed, cited
- Kimi K2.6 optimizes model inference in Zig, a highly niche programming language, to demonstrate exceptional out-of-distribution generalization.
- The model reconfigured the exchange-core thread topology from 4ME+2RE to 2ME+1RE to extract a 185% medium throughput leap.
kimi.com2026-01-27officialauthorityHN front pageabout the Kimi K2 familyHN 502 pts · 239 comments1,856 words
Kimi K2.5 self-directs an agent swarm with up to 100 sub-agents executing parallel workflows across up to 1,500 tool calls. This swarm architecture reduces execution time by up to 4.5x compared to a single-agent setup without predefined workflows.generated, cited
kimi.comofficialauthorityabout the Kimi K2 family1,329 words
Kimi K2 is a Mixture-of-Experts model with 32 billion activated parameters and 1 trillion total parameters that is now open-sourcing Kimi-K2-Base and Kimi-K2-Instruct. The model was pre-trained on 15.5T tokens using the MuonClip optimizer, which stabilizes training via a qk-clip technique to prevent exploding attention logits. Users can deploy it on engines like vLLM or SGLang, and examples show it generating insights through 16 IPython calls or orchestrating 17 seamless tool calls for travel planning.written, reviewed, cited
- The model is a reflex-grade Instruct variant that operates without long thinking capabilities.
- Vision features are currently not supported for the Kimi K2 model.
- One-shot prompting yields performance degradation compared to using the model under an agentic framework.
Analysis6
github.blog2026-07-02authorityHN front pageabout the Kimi K2 familyHN 417 pts · 185 comments317 words
Kimi K2.7 Code is generally available in GitHub Copilot as the first open-weight model offered as a selectable option in the Copilot model picker. The model is beginning to roll out to Copilot Pro, Pro+, and Max plans within Visual Studio Code version 1.127.0 or later, while it remains off by default for Copilot Business and Copilot Enterprise requiring plan administrators to enable the policy. Rollout will be gradual as GitHub continues to monitor the model's quality and performance.written, reviewed, cited
moonshotai.github.io2025-11-06HN front pageabout the Kimi K2 familyHN 936 pts · 427 comments34,041 words
Kimi K2 Thinking is an open-source thinking agent model that executes up to 300 sequential tool calls to solve complex problems. The model achieves 44.9% on HLE with tools, 60.2% on BrowseComp, and 71.3% on SWE-Bench Verified. It demonstrated deep reasoning by solving a PhD-level mathematics problem through 23 interleaved reasoning and tool calls.written, reviewed, cited
- The model marks latest efforts in test-time scaling by scaling thinking tokens and tool calling steps.
- K2 Thinking is live on kimi.com under the chat mode with full agentic mode available soon.
github.com2025-07-12authorityHN front pageabout the Kimi K2 familyHN 352 pts · 2 comments2,355 words
github.com2025-07-21authorityabout the Kimi K2 familyHN 84 pts · 6 comments
arxiv.orgauthorityabout the Kimi K2 family
huggingface.coauthorityabout the Kimi K2 family
Community1
twitter.com2025-07-11HN front pageabout the Kimi K2 familyHN 348 pts · 179 comments
