Coding Tools
Kimi K2.6 Powers Autonomous Code Generation
Cole Medinmedium confidence
Why it matters
- →This project showcases the capabilities of AI in automating software development processes, potentially transforming how code is written and managed.
Cole Medin has announced the deployment of Kimi K2.6 in his AI Dark Factory, a project focused on autonomous code generation. The factory currently includes functionalities such as triaging GitHub issues, creating pull requests from scratch, and validating its own outputs to prevent errors. Medin is now comparing the performance of Kimi K2.6 against the previous model, MiniMax M2.7, while also integrating this into the RAG agent platform. This development highlights advancements in AI-driven coding tools and their potential for fully automated software development.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Public Experiment on AI Dark Factory Launched
Cole Medin · April 16, 2026 · Related
What happened next
- 2Kimi K2.7 Code Rivals Claude Fable 5 in Landing Page Test
Together AI Blog · June 17, 2026 · Related
- 3Kimi K2.7 Code Now Available in GitHub Copilot
GitHub Changelog · July 1, 2026 · Background
- 4Moonshot releases Kimi K3 with 2.8 trillion parameters
Fireship · July 22, 2026 · Background
- 5Kimi K3: Largest Open-Weight AI Model Released
Together AI Blog · August 1, 2026 · Background
- 6Cole Medin's AI Dark Factory: Autonomous Coding Workflow
Cole Medin · August 14, 2026 · Same story
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.323 adds experimental Code Mode and plugin safety
This release quietly introduces Code Mode, an opt-in feature where Claude writes JavaScript to call its own tools, marking a shift toward more autonomous agent-like behavior within the CLI. The update also hardens the plugin ecosystem by enforcing version ranges and adding strict TypeScript type checking for hooks, which should significantly reduce instability from third-party extensions. Beyond these features, the changelog is dominated by critical fixes for authentication drift in background sessions and memory leaks when handling large files, stabilizing the tool for heavy enterprise use.
Claude Code Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12343 adds qwen3.5 and ROCm 10
This release quietly extends llama.cpp’s hardware coverage with ROCm 10.0 binaries for both Linux and Windows, finally bringing AMD RDNA/CDNA users into the fold without manual compilation. The standout feature is native support for Qwen3.5 models via tensor merging during conversion, a necessary step as this new architecture gains traction in the open-source community. By shipping pre-built CUDA 13 binaries alongside the older 12.x versions, the project ensures forward compatibility with newer NVIDIA GPUs out of the box. There are no new quantization algorithms or performance breakthroughs here; it is purely an infrastructure update to keep pace with the rapidly shifting landscape of model architectures and GPU drivers.
llama.cpp Releases