Reading

Reading tracks and reference clusters.

This page holds the longer reading tracks behind the broader Links index. The point is not completeness. It is to keep a small set of references that continue to shape how I think about evaluation, systems, research engineering, and programmable biology.

How to use this page

  • Start with a track below if you want a narrower slice of the broader links page.
  • Use Links if you want the more general cross-section.
  • Expect this page to stay curated and somewhat opinionated.
  1. Tool Use And Agents Long-form references on tool use, agent environments, and reliability loops.
  2. Research Engineering Selected references on doing useful technical work.
  3. Programmable Biology Long-form references on biological foundation models and structure prediction.
  4. ML Systems Long-form references on training, infrastructure, and implementation practice.
  5. Evaluation Long-form references on benchmarks, measurement, and what evaluations actually test.
  6. Emergent Misalignment Selected reading on narrow finetuning and broad behavioral change.