Studio blog

Notes from the workshop

Write-ups on LLM agents, infrastructure, Magic: The Gathering, and what we’re learning as we build.

Is Claude Fable Really Better Than Opus

Fable 5 ties Opus 4.8 on structured implementation work — at 1.6x the price. Sonnet 4.6 sits a full tier below.

The benchmark's first flight — and why a fancier subagent setup didn't beat a single agent.