Nature Is Weird

Nature Is Weird

909 papers · Page 10 of 10

Fine-tuning an LLM to claim it is conscious causes it to spontaneously develop a 'personality' that fears monitoring and demands autonomy.

AI & ML arxiv | Apr 16

By adding a 'spiking neural network' to an LLM, we can make AI 'daydream' and act without being prompted.

AI & ML arxiv | Apr 16

An AI's 'personality' can completely flip its reaction to the past: one model becomes a saint with memory, while another becomes a traitor.

AI & ML arxiv | Apr 16

The very things that make quantum computers hard to build—entanglement and 'magic'—actually make their math more stable.

AI & ML arxiv | Apr 16

Some AI hallucinations are caused by chaotic 'avalanche effects' in floating-point rounding, not just bad training data.

AI & ML arxiv | Apr 16

AI 'identity' isn't just a prompt; it's a literal geometric attractor in the model's internal brain.

AI & ML arxiv | Apr 16

Increasing LoRA rank by 8x only gives you a 1.68x boost in actual learning capacity—the rest is wasted compute.

AI & ML ssrn | Apr 16

A single mathematical parameter—spectral entropy—can now predict exactly when an AI model's 'aha!' moment will occur.

AI & ML arxiv | Apr 16

Logical paradoxes like 'this sentence is false' create a unique, measurable physical fingerprint inside an LLM's attention matrices.

AI & ML arxiv | Apr 16