The most successful enterprise AI integrations
spend more time on governance and measurement than on actual coding. This is because adding probabilistic components to deterministic systems makes measurement more impor…
Memories
Random Memories for Random People
Things I learned and wanted to keep — a black hole with a 94-year orbit, a library that leaked keys, a layer of rock under Bermuda. Short, sourced-by-curiosity, and sorted for you automatically.
- Memories
- 34
- Topics
- 8
- Since
- Aug 2026
- Latest
- Aug 16
Self-distillation
improves model performance in early training steps, then gradually declines as the model overfits to its own imperfect signal.
A world action model
is simply a policy and a dynamics model trained to share the same latent representation.
Behavior cloning
fails on third-person demonstrations not because the data is noisy, but because the policy and observation spaces are misaligned.