Reading up on Sonnet
3 deep · digging since mar 11
- Fable's judgement
The author learned to let Claude Code's Fable model use its own judgement to delegate coding tasks to lower-power models, improving efficiency and token usage.
- Autoresearch, Claude and Constrained Optimization
An experiment using Claude Code to autonomously optimize a file compression algorithm over 10 iterations, achieving competitive results against standard tools by iterating on an LZSS-based approach.
- Why I believe in SOTA models over custom ones
The future of AI is powerful general models becoming cheaper, not narrow custom models, because specialized tasks still benefit from broad intelligence.