togatoga/karukan
Summary
Karukan is a neural kana-kanji conversion input method system for Linux/macOS, using llama.cpp to run the GPT-2 model, supporting real-time conversion, context awareness, and user learning.
View Cached Full Text
Cached at: 07/01/26, 11:30 AM
Karukan
Japanese input system for Linux and macOS — Neural kana-kanji conversion engine
Similar Articles
Computer History in ChatGPT
OpenAI is introducing Computer History in the macOS desktop app, capturing local interaction events (clicks, typing, app switches, etc.) to let ChatGPT and Codex remember how users work, thereby providing a more personalized agent experience, with privacy controls and automated suggestions.
@yibie: Recommend this repo to build a GPT-style transformer from scratch without any advanced libraries. With 13M parameters, it can produce grammatically correct text, trainable in one day on a free Colab T4. Train your own LLM from scratch: 13M parameter GPT implementation - Akshay shares…
Recommended a GitHub repo for building a GPT-style Transformer from scratch without advanced libraries. With 13M parameters, it can be trained in one day on free Colab to generate grammatically correct text.
Introducing gpt-transcribe and gpt-live-transcribe
OpenAI has released GPT-Transcribe and GPT-Live-Transcribe, two transcription models designed for batch processing of full files and real-time streaming, respectively. They support 57 languages, custom vocabulary, and automatic language switching, with improved performance in challenging conditions like accents and background noise.
@axiaisacat: ByteDance has open-sourced an AI called UI-TARS that can directly control your computer. It is open-source, free, and runs locally. You tell it using natural language: 'Book me the earliest flight from San Francisco to New York on September 1st on Priceline', 'Set the auto-save delay in VS Code to 500ms', '...'
ByteDance has open-sourced UI-TARS, an AI model capable of directly controlling computer interfaces via mouse and keyboard for tasks like booking flights or configuring software. Available in 2B, 7B, and 72B parameter sizes, it runs locally and offers a free alternative to paid services like Anthropic's Computer Use.
@hank_aibtc: Family, local LLMs are incredibly impressive! I stumbled upon this gpt-oss-20b-tq3 on Hugging Face, and it's truly captivating! OpenAI's official open-source 20B+ parameter MoE model, optimized by the community using TurboQuant 3-bit quantization + MLX...
The article highlights the gpt-oss-20b-tq3 model, a quantized version of an OpenAI MoE model that runs efficiently on standard 16GB MacBook Airs using TurboQuant and MLX optimizations.