RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One topic. Every takeSeek and you shall find

Reading up on experimentation

1 deep · digging since mar 12

  • delip.github.io favicon
    Artifact Viewer

    A protocol for an autonomous LLM agent to iteratively experiment with modifying a language model training script under fixed time and resource constraints, automatically keeping or discarding changes based on validation bits-per-byte improvement.