Self-Actualization Is No Different from a Pufferfish's Sand Circle
Kenrick’s evolutionary reconstruction of Maslow’s hierarchy, and how digital services exploit our evolved motivational systems.
Posts
Two Minds in One Brain: Why We Act Irrationally Even When We Know Better
Why can’t you resist that midnight snack during a diet? Two independent processing systems live inside your head: one that calculates and one that feels. A look at Pacini & Epstein’s 1999 study on the Rational-Experiential Inventory.
Uri Alon's Systems Biology: The Free Lectures
Uri Alon reads the living cell the way an engineer reads a circuit, and his whole course, lectures, notes, and exercises, is free. Where to get it, to open this series.
The Model Efficiency series has moved to the company blog
The story of making neural networks smaller and faster (number formats, quantization, pruning, and so on) is now serialized on the company blog. Here is where to go.
The Idea That Lost and Came Back: Skinner, Chomsky, and the Talking Machines
One man argued that language was a matter of reward and habit, and lost famously. Half a century later, the machines that talk to us are trained with exactly that: reward.
Sentence Reranking Using LLM Attention Maps
Leveraging what the LLM already knows. An experiment extracting document relevance signals from Attention Maps to rerank sentences, along with a survey of related papers.
Transformer Circuits 7: The Related-Work Landscape
Reading the Framework paper, final part. Whose shoulders this paper stands on, and how its approach differs from the lines of work before it.
Transformer Circuits 6: Where Does This Leave Us?
Reading the Framework paper, part 6. What the framework secured and what it did not: the wall called MLP, and the follow-up research this paper announces.
Transformer Circuits 5: Two-Layer Models and Induction Heads
Reading the Framework paper, part 5. With two layers, heads compose with heads: Q-, K-, and V-composition, and the paper’s biggest discovery, the mechanism of the induction head.
Transformer Circuits 4: One-Layer Models and Skip-Trigrams
Reading the Framework paper, part 4. Fully expanding a one-attention-layer model into paths: skip-trigrams, copying heads and positive eigenvalues, and the characteristic bugs the factored structure produces.