This page has a curated list of personal reading. I have personally benefitted from other people's curations and this is simply a way of giving back to the community. It primarily curates from reading material I come across every day while working on problems or learning about things I care about the most.

  1. Multi-Turn Papers on multi-turn degradation, recovery, and interaction-centric failure analysis.
  2. Tool Use And Agents Long-form references on tool use, agent environments, and reliability loops.
  3. Research Engineering Selected references on doing useful technical work.
  4. Programmable Biology Long-form references on biological foundation models and structure prediction.
  5. ML Systems Long-form references on training, infrastructure, and implementation practice.
  6. Evaluation Long-form references on benchmarks, measurement, and what evaluations actually test.
  7. Emergent Misalignment Selected reading on narrow finetuning and broad behavioral change.