Reading Notes

Notes and summaries from reading ML/AI papers (and some blog posts). All credit to the content in the papers and blog posts goes to the original authors.

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

Multiagent Fine Tunes

1 min read · November 30, 2025

2025 · distillation
ML Tea: Planning and Problem-Solving with General, Scalable Neuro-Symbolic Models

ML Tea LLMs \+ symbolic computing

4 min read · November 24, 2025

2025 · partial-read · distillation
Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent

SAIA

2 min read · November 24, 2025

2025 · distillation
Continuous Language Model Interpolation yields Dynamic and Controllable Text Generation

continuous model interpolation with lora

1 min read · November 23, 2025

2025 · distillation
Natural Emergent Misalignment from Reward Hacking in Production RL

Anthropic emergent misalignment

5 min read · November 23, 2025

2025 · distillation