
In a recent livestream, Cole Medin demonstrated the capabilities of an AI coding agent by building a codebase entirely autonomously, without human code review. The project, named Dark Factory, utilizes Medin's open-source AI coding orchestration platform, Archon, to create a real application that answers questions about his YouTube content. The process includes defining governance files, managing GitHub issues, and implementing workflows that allow the AI to generate pull requests and validate its own code. This ambitious project reflects the evolving landscape of AI in coding and aims to push the boundaries of automation in software development.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
AI Explained · December 23, 2025 · Background
Together AI Blog · February 25, 2026 · Background
Lev Selector · March 6, 2026 · Related
Cole Medin · April 25, 2026 · Related
Cole Medin · April 28, 2026 · Related
WIRED AI · May 26, 2026 · Related
TechCrunch AI · June 22, 2026 · Background
TechCrunch AI · August 5, 2026 · Background
AI Dark Factory: Codebase Writes Itself Live
3 developments
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.
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.
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.