Readings
Books, papers, articles, and references worth tracking.
- ·research
The Unreasonable Effectiveness of *
Wigner's 1960 essay on why mathematics fits the physical world at all — and the whole genre of successor titles it spawned.
- ·research
The free-energy principle: a rough guide to the brain?
Friston's short, readable entry point to the free-energy principle — perception, action, and attention as one variational bound.
- ·research
The Bitter Lesson
Rich Sutton's short essay arguing that general methods leveraging computation beat hand-built human knowledge, every time, over the long run.
- ·research
Reward is Enough
Silver, Singh, Precup, and Sutton's maximalist hypothesis — that every ability we call intelligence falls out of maximizing a single scalar reward.
- ·personal
Psalm 88
The one psalm that never resolves — a lament that walks all the way into the dark and stops there.
- ·personal
Oh, the Places You'll Go!
Dr. Seuss's last book, and a surprisingly unsentimental map of the Waiting Place, the Lurch, and the slump you are supposed to get out of.
- ·personal
Man's Search for Meaning
Viktor Frankl's account of the camps and the logotherapy he built from it — meaning as the thing that survives when everything else is taken.
- ·writing
I Have a Dream
King at the Lincoln Memorial — the speech I return to for what rhetoric can do when the argument and the cadence are the same thing.
- ·research
Grokking: Generalization Beyond Overfitting
The paper where validation accuracy jumps from chance to perfect long after the training loss flatlined — generalization as a delayed phase change.
- ·research
The Brain from Inside Out
Gyorgy Buzsaki's inside-out account of brain function, emphasizing self-organized activity and action-led cognition.
- ·research
Rhythms of the Brain
Gyorgy Buzsaki's major synthesis of neural oscillations, timing, and the rhythmic organization of cognition.
- ·research
Pretrained Transformers as Universal Computation Engines
A study of frozen pretrained transformers as reusable computation engines across non-language sequence tasks.
- ·research
On the Measure of Intelligence
Francois Chollet's proposal to measure intelligence as skill-acquisition efficiency rather than task skill alone.
- ·research
Language Models are Few-Shot Learners
The GPT-3 paper that made in-context learning a central empirical phenomenon in modern AI.
- ·research
Attention Is All You Need
The Transformer paper that made attention-only sequence modeling the default substrate for modern language models.
- ·writing
A Beautiful Loop
Current reading notes on the active-inference account of consciousness and the recursive loop that makes a model include itself.