All variants of huihui-ai's Qwen 3.5 abliterated produced garbage tokens. GLM-4.7-Flash abliterated had a broken chat template. The official version with thinking disabled turned out to be the right answer.
After a macOS update, tmux sessions started by cron lost access to the Keychain, causing Claude CLI batch jobs to silently fail. Diagnosing the issue, the fix, and why this is a structural macOS Keychain problem rather than a Claude CLI bug.
Experiment log: from LUKE/BERT fill-mask fine-tuning, to perplexity-based error detection, to Qwen2.5 7B correction judgment with human escalation on mismatch. A complete pipeline running on a single RTX 4060 Laptop with 8GB VRAM.
From Docker hell to Lite + LLM correction. A retrospective on my own experimentation, plus an introduction to someone else's browser-based NDLOCR-Lite implementation.
Set up the CLI version of NDLOCR-Lite on Apple Silicon Mac, then tested OCR result correction with Qwen 3.5 and Swallow. Includes experiments with direct image reading and the anchoring effect.
Tried the lightweight OCR tool NDLOCR-Lite released by the National Diet Library — installed it on Windows 11 and tested both the CLI and GUI versions.
Design and implementation of Kana Chat, a personal AI agent system that wraps official CLIs. Covers the tmux bridge, context isolation, and tool approval gate that make it safe to run in your own environment.
How to configure VRAM/main memory split on the GMKtec EVO-X2 (Strix Halo) for local LLM inference. A 29.6GB model ran fine with just 8GB of dedicated VRAM.
Building an NSFW-capable local LLM on the GMKtec EVO-X2 (Strix Halo). Getting GPU inference at ~11 tokens/s with LM Studio and MS3.2-24B-Magnum-Diamond.
Upscaling images loaded via the Load Image node was producing garbled output. Fixed it by addressing the non-contiguous tensor issue — a one-line patch to comfy/utils.py.
