What's the best AI model for Jewish textual research?
A friend asked me which AI model is best for Jewish textual research. The answer is that it's the wrong question — the model isn't where the knowledge lives. Here's what to do instead.
Tech Blog · by Daniel Rosehill
Hey, It Works!
Technical deep-dives, project showcases, and tool writeups — short notes on the things I build, break, and occasionally get working.
Latest posts
View all 138 posts → 
A Claude Code plugin for filing better feedback to Anthropic
Latest addition to my Claude Code marketplace: a self-healing plugin that turns the agent itself into a feedback-filer. Interviews you against the live Anthropic issue templates, renders the body in the right format, and files via gh.
Three repos for running purchasing decisions through Claude Code
A pattern I've settled into for buying things thoughtfully: one repo per purchase, standing preferences in Mem0, an Israel-specific plugin that handles the local retail quirks, and two workspace templates that split product merit from sourcing.
AI Typer V2 — v0.5.5
Voice dictation with single-pass multimodal cleanup. Gemini 3 Flash is the new default; Debian package available.
How much bitrate does an audio-multimodal LLM actually need?
An eval across 12 audio-capable models on OpenRouter, 5 MP3 bitrates, 4 dictation samples. The default upload quality in most dictation apps is 2–4× overprovisioned — and the more interesting finding had nothing to do with bitrate.