The three-stage pipeline of BERT perplexity scan → LLM judgment → escalation packaged as a cross-platform Python tool. The installer automatically downloads llama-server and GGUF models.
On March 19, 2026, Anthropic took legal action against OpenCode to remove the OAuth integration. On the same day, Python toolchain Astral announced that it was joining OpenAI's Codex team. The formation of AI coding tools was activated in one day.
CLI-Anything, released by HKUDS at the University of Hong Kong, automatically generates a CLI harness from GUI software source code so AI agents can drive it directly. It passed all 1,720 tests across 16 apps including GIMP, Blender, and LibreOffice.
Project Detroit announced by Oracle at JavaOne 2026. We proposed to OpenJDK the idea of directly incorporating V8 and CPython into Java builds and calling them using the javax.script API. After the abolition of Nashorn and GraalVM's withdrawal from the Java cycle, why did they now turn to ``embedding the native runtime'' instead of ``in-house implementation''?
A summary of the dispute in which chardet's original author argues that the LGPL-to-MIT relicensing was invalid, and the formal launch of the React Foundation under the Linux Foundation. Two very different cross-sections of OSS governance.
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.
