Offical code for the paper ''Thought without systematicity? Evaluating reasoning models on rule induction tasks" - smonsays/systematicity-eval

We were wrong about the Uncanny Valley.

On AI agents, grunt work, and the part of science that isn't replaceable.

Nicholas and Mattar found that people use episodic memory to make decisions when it is unclear what will be needed in the future. These findings reveal how the rich representational capacity of episod...

Many recent studies have found evidence for emergent reasoning capabilities in large language models, but debate persists concerning the robustness of these capabilities, and the extent to which they ...

I first encountered Principles of Neural Science as a young student of neuroscience. The book was filled with delightful narratives…

The neocortex is organized into functionally specialized areas. While the functions and underlying neural circuitry of individual neocortical areas are well studied, it is unclear how these regions op...

Feeling a bit wired

By Kristopher T. Jensen. Reinforcement learning for neuroscientists

Systems-level biology is hard because systems-level engineering is hard.

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning...

Official code for the paper "Attention as a Hypernetwork" - smonsays/hypernetwork-attention

Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training but whose compositions have not. What mechanisms und...