moonshotai/Kimi-K2.7-Code

kept by eddie jun 15

Moonshot AI releases Kimi K2.7 Code, a 1T-parameter MoE coding model that improves real-world agentic tasks while cutting thinking tokens by 30% over K2.6.

DSHR's Blog: Distilling The Moat
The article argues that AI companies’ claimed moat from expensive model training is shallow because model distillation allows competitors to cheaply replicate capabilities via repeated API queries.
also on Moonshot AI, DeepSeek
GitHub - MoonshotAI/kimi-code: Kimi Code CLI — The Starting Point for Next-Gen Agents
Kimi Code CLI is a terminal-based AI coding agent that reads, edits code, runs commands, and integrates with editors via the Agent Client Protocol.
also on Moonshot AI, #ai-agents, #ai-coding, #developer-tools
Introducing FrontierCode
Cognition's FrontierCode benchmark measures code mergeability, finding even top models like Claude Opus 4.8 score only 13.4% on its hardest 50 tasks.
also on GPT-5.5, #benchmarks, #open-source, #ai-coding, #developer-tools
Surpassing Frontier Performance with Fusion — OpenRouter Blog
OpenRouter's Fusion, which synthesizes outputs from multiple language models via a judge model, outperformed individual frontier models including GPT-5.5 and Claude Opus 4.8 on deep research tasks, with a budget panel achieving near-frontier performance at half the cost.
also on GPT-5.5, #benchmarks, #ai-coding, #developer-tools
8 plots that explain the state of open models
Qwen dominates open-model downloads and finetunes globally, while DeepSeek leads in large-scale models and GPT-OSS is the only Western contender gaining adoption.
also on DeepSeek, #benchmarks, #open-source, #developer-tools