Wiring up Obsidian’s Whisper plugin to the free Cloudflare-backed OpenAI API from the previous post.
Wrapping Cloudflare’s free Workers AI models (including Qwen) behind an OpenAI-compatible endpoint, so existing front-ends don’t need to change a line of code.
Obsidian’s sync to Typecho doesn’t support custom fields over XML-RPC, so I patched the theme instead.
Adding a caching plugin for faster page loads, plus wiring up Google Analytics.
A quick note on a comparison table of large-model offerings across major cloud providers.
Some hands-on experiments with un-tuned open models, and a few thoughts on where the real value in LLM products actually sits.
Elmo can summarize any page on the fly — and it turns out that’s genuinely useful for reading in a second language.
Getting Immich running on a home NAS and bulk-uploading years of photos with the CLI.
Google says usage was too low to justify keeping the feature around.