Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers
teortaxesTex · x · 2026-09-11
Moonshot AI has fully rolled out K2.8 Preview in Kimi Code, keeping the same model ID (kimi-for-coding) so no client changes are needed.
Key points:
- Coding and agent capabilities improved across the board, with notably more efficient thinking than K2.7 Code; performance is claimed to be close to K3.
- Adjustable thinking effort: low / high / max (default max); requests with thinking off are served by K2.8 Preview.
- 1M-token context window now available on all membership tiers.
Kimu Code CLI v0.41.0 also adds an experimental Tower multi-agent mode in Web, text-selection annotations, and no longer blocks dangerous commands. A separate commentator notes K3's architecture looked impressive but may not be servable at scale, forcing design around real inference-bottleneck economics.
More from coding & agent
- Inspired by OpenAI's 10,000-agent run, dev open-sources a crowdsourced agent problem-solving platform — Benjaminsen · 2026-09-11
- Lucid: open-source Mac app keeps your laptop awake only while AI agents run — Pitiful_Hedgehog_600 · 2026-09-11
- banteg's snail project crowdsources AI agents to finish matching Snail Mail's 20 remaining functions — banteg · 2026-09-11
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11