Since so many people asked how I use Claude Code I might share a session. But I would need some ideas what small scale problem should be implemented. Give me some good ideas and I might do it.

PostgreSQL, the open source database that continues to get better, is introducing oauth support. This should help with database automation and hopefully bring us one step closer to moving away from static credentials and copying usernames and passwords around. www.postgresql.org/about/news/p...

I've got only one resolution. Stay focused.

Mostly: "We are a small publisher, we received this manuscript for a sci-fi short story. We only publish top quality stuff, we don't want any garbage. Please tell us if this story is worth publishing in our high quality series". And identify when Claude is right, make changes 2/3 days. Retry.

The first step in my career was learning how to do things, but it took understanding why I was doing them for my career to take off. I went from completing tasks to asking why, then understanding the impact of my work, and eventually gained the ability to find the most impactful things to work on.

qwq is a new openly licensed LLM from Alibaba Cloud's Qwen team. It's an attempt at the OpenAI o1 "reasoning" trick that runs on my Mac (20GB download) via Ollama... and it's pretty good!

My detailed notes here: simonwillison.net/2024/Nov/27/... - here's its attempt an SVG pelican riding a bicycle.

Anthropic released an interesting thing today: an attempt at a standard protocol for LLM tools to talk to services that provide tools and extra context to be used other the models modelcontextprotocol.io