~/categories $ cat AI
// AI
5 posts in this category.
From One Agent to a Team: Async Loops, Multi-Agent Personas, and an Autonomy Envelope for Cline
The next step after steering a single coding agent is letting it run unattended and splitting it into specialised personas. Here is the honest, safety-first version: a GREEN/AMBER/RED action envelope that defines what...
Teaching Cline to Learn From My Corrections: Turning Conversation Steering Into Durable Rules
Self-learning AI agents promise to get smarter from every interaction. Here is the honest version for a coding agent like Cline: it does not retrain its own weights from your chats, it consolidates your corrections in...
How I Steer Cline With a Tiered Rules System, a Persona, and a Pre-Commit Hook That Stops Me Leaking My Homelab
A 700-line steering layer for Cline split into always-on rules and on-demand reference docs, a banned-words list that kills the AI smell, opsec rules that keep internal hostnames out of public commits, a single canoni...
Running ComfyUI on an AMD RX 7900 XTX — Native ROCm 7.1 on Windows
How I got ComfyUI running natively on an AMD RX 7900 XTX on Windows 11 using ROCm 7.1, without Zluda, with Wan2.1, LTX-Video, and FramePack custom nodes — and the exact steps to replicate it.
Zero-Shot Voice Cloning on AMD — ROCm 7.1 on Windows, F5-TTS, and the ONNX Fallback
How I got zero-shot voice cloning running on a Windows gaming machine with an AMD RX 7900 XTX — using ROCm 7.1 natively on Windows, with an ONNX+DirectML fallback for when you don't want the full SDK.