An arXiv paper reports that fine-tuning GPT-4o, Gemini 2.5 Pro, and DeepSeek-V3.1 on summary-to-text expansion tasks increases verbatim reproduction of copyrighted books.
Three local image generation engines (WAI-Anima, WAI-IL/SDXL, FLUX.2 Klein 4B) tied together by a thin FastAPI wrapper that takes Japanese prompts. Ollama (gemma3:12b) handles JP→EN, ComfyUI workflows are built on the fly in Python, FLUX.2 runs as an mflux subprocess, and the whole thing is reachable from an iPhone over Tailscale.
VoteWise AI turns election education into a multilingual chat, voice, and story-mode experience built on Next.js. Notes on designing around Gemini 2.5 Flash's safety filters in a political context.
Hands-on log of building the DEV article's PDF RAG on M1 Max 64GB, extending it with images via CLIP, and pushing through Japanese with bge-m3 + Qwen3.6 35B. Documents the modality gap, the dual inference server crash, and LLM-jp 4-8B's empty chat template silently dropping the system role.
Notes on a DEV Community article that wires up FastAPI as an OpenAI-compatible RAG API layer with llama.cpp, Chroma, and Open WebUI, plus where the architecture fits and what to watch for.
A read of arXiv:2604.26622 OCR-Memory. It renders agent execution history into images, uses Set-of-Mark to let a VLM pick relevant segments, then retrieves verbatim text from the original logs.
A hands-on log of running Qwen-Scope's Sparse Autoencoder locally on M1 Max 64GB with Qwen3-8B-Base, extracting feature IDs that discriminate between Japanese, English, code, and Chinese from a single middle layer.
The Qwen team released Qwen-Scope, a Sparse Autoencoder suite for Qwen3/Qwen3.5. 14 groups of SAEs covering inference-time steering, evaluation analysis, toxicity classification, data synthesis, and training improvement.
NII/LLMC released CC Audio and Archive.org Audio Dataset. URL lists, metadata, and a downloader covering 48,000+ hours of Japanese audio. What it actually contains and how it fits into TTS, ASR, and audio model training.
Hands-on benchmark of FLUX.2 Klein 4B on M1 Max 64GB using mflux (MLX) and iris.c (pure C + Metal). A counter to Pruna AI's H100-only tutorial — measuring how fast Apple Silicon actually gets there.
Designing field-level confidence thresholds for human-in-the-loop document extraction, and the OCR and threshold walls hit when automating journal entries with freee MCP.
After Xiaomi MiMo-V2.5's weights went public, I checked whether it runs on Mac/ROCm or on cloud GPU (RunPod/GCE). It's still rough on local hardware, but RunPod's 4x H200 runs it for ~$14/hr and GCE Spot H100 brings it down to ~$1.6/hr.
