AI

Turning family photos into cartoons, adding a warship and a dinosaur to travel pictures, and restyling a portrait — a weekend with ChatGPT-4o’s new image tools.

Ten dollars a month for autocomplete that actually understands what I’m writing.

A quiet rollout, a tight usage cap, and a version that’s clearly a big step up on reasoning.

Offloading transcription from a GPU-less NAS to a desktop with an actual GPU, exposed as a simple internal API.

A simple script to auto-transcribe Obsidian voice notes, derailed twice by the NAS running out of space in root and /tmp.

Chatting with my own notes via a local model, plus a gotcha when pointing the plugin at a self-hosted One API server.

Running ten locally-hosted models on consumer GPU hardware to see which ones best summarize customer-service calls after speech-to-text.

What an ‘agent’ actually means in the context of large language models, and a worked example in a customer-service setting.

After AMD’s ROCm ecosystem let me down for local fine-tuning, free Colab GPUs turned out to be the pragmatic way to fine-tune Llama 3 for free.

Self-hosting the open-source MaxKB knowledge-base tool at home, and pointing it at a Qwen-backed model for Chinese-language documents.

Pairing a consumer GPU running local Llama 3 with Open WebUI and One API to combine local and remote models behind one interface.

Wiring up Obsidian’s Whisper plugin to the free Cloudflare-backed OpenAI API from the previous post.