§ 05
·
Links
·
A scrapbook
Things worth the click.
A scrapbook of papers, essays, blogs, and tools I’ve enjoyed on the internet. Updated when I remember. No promises about freshness.
Papers
- 2017 Attention Is All You Need Vaswani et al.
- 2020 Scaling Laws for Neural Language Models Kaplan et al.
- 2022 Toy Models of Superposition Elhage et al., Anthropic.
- 2023 Universal and Transferable Adversarial Attacks on Aligned LLMs Zou et al.
- 2024 Scaling Monosemanticity Templeton et al., Anthropic.
- 2024 Sleeper Agents Hubinger et al., Anthropic.
- 2024 Stealing Part of a Production Language Model Carlini et al.
- ref The Feynman Lectures on Physics Caltech free online edition.
Essays & people
- essay You and Your Research Richard Hamming. Canonical UVA transcript.
- essay Otherness and Control in the Age of AGI Joe Carlsmith.
- people Nicholas Carlini on research & craft “How to win a best paper award” (2026) is the obvious entry point.
Blogs I read
- blog Commoncog Cedric Chin. The Tacit Knowledge and Becoming Data Driven sequences.
- blog Gwern.net Gwern Branwen. “On Really Trying” is a useful entry point.
- blog Joel on Software Joel Spolsky.
- blog Neel Nanda’s mech interp hub
- blog Nintil José Luis Ricón.
- blog Transformer Circuits Thread Chris Olah and collaborators.
- blog What’s new Terence Tao.
Tools I rely on