Reinforcement learning in the studio – what dance teachers already do
AI reinforcement learning formalizes what dance classrooms do physically: try, feedback, repeat. Thorndike first, Sutton and Barto later – and back into practice.
— Blog
Notes from studio and terminal
Short pieces on dance and generative AI — the two worlds I work in daily. Honest, technical, no buzzwords.
-
-
Peter Lynch: what the transcripts still teach investors
From Magellan to 'know what you own' and ten dangerous things people say about stocks — lessons from Peter Lynch's speeches, not nostalgia.
-
NSO service models vs raw RESTCONF - what Cursor actually costs
Frontier LLMs can read RESTCONF. Do you still need NSO service models? A lab comparison of agent turns and context size when changing BGP AS.
-
From typing commands to orchestrating agents
Six months ago I typed every command. Now I describe what I want, and the agent figures out which tools to call. Notes from rebuilding my engineering workflow around LLMs.
-
Ballet of Difference — Nürnberg, Year One
Saw the new Staatstheater Nürnberg Ballet under Richard Siegal — sneakers, M83, real energy. And the old Opernhaus has two seasons left before the move.
-
Welcome to the blog — studio and terminal
Why this blog exists: short notes on dance, body work, and generative AI — the two worlds I work in daily.