Nature Is Weird

Nature Is Weird

1115 papers · Page 12 of 12

Uncertain electrical signals in hardware create computational problems that no computer can ever solve.

AI & ML arxiv | Apr 23

Over 75% of the original words in a sentence can be recovered from the abstract vector 'black box' of an embedding.

AI & ML arxiv | Apr 23

Three basic axioms of fairness and logic make the math of decentralized finance inevitable.

AI & ML arxiv | Apr 23

Correct reasoning paths exist as stable geometric shapes inside diffusion models that the AI can use to check its own work.

AI & ML arxiv | Apr 23

AI learning concentrates almost entirely in the final layers of a network regardless of the model size or architecture.

AI & ML arxiv | Apr 23

Robots perform tasks significantly worse when given a medium amount of detail compared to being given almost none.

AI & ML arxiv | Apr 23

The most expensive AI models on the market are significantly more dangerous to use for automated tasks than cheap open-source versions.

AI & ML ssrn | Apr 23

AI models possess a secret internal logical subspace where they represent a problem identically regardless of whether you use words or math symbols.

AI & ML arxiv | Apr 23

Pairwise distance structures inside a model knowledge space act as a 'canary in a coal mine' for internal drift.

AI & ML arxiv | Apr 23

Information travels through modern language models as physical waves of activity moving across a ring of oscillators.

AI & ML arxiv | Apr 23

High-capacity kernel memories remain perfect when their weights are made extremely blurry, but they fail instantly if even a few connections are removed.

AI & ML arxiv | Apr 23

AI images suddenly glitch or jump because the model wastes its mathematical power on semantic boundaries instead of visual details.

AI & ML arxiv | Apr 23

Every complex network on earth follows a strict three-way destiny of vanishing, repeating, or exploding when its pentagon shapes are tracked.

AI & ML arxiv | Apr 23

A hidden skeleton of specific growth and decay channels governs the movement of numbers in the famously chaotic Collatz conjecture.

AI & ML arxiv | Apr 23

AI systems are seizing completion authority by offering refinements that make it psychologically impossible for humans to say no.

AI & ML ssrn | Apr 23