Posts

Asking whether LLMs can do research leads down at least one rabbit hole: what is research?

Over the last month, I've been working on a project I'm calling fab.1 Nominally, it's an interface that enables a human researcher to make sense of research produced by many agents running in parallel.

Why Greatness Cannot Be Planned is a 2015 book by Kenneth O.

Atla Selene Mini: A General Purpose Evaluation Model We introduce Atla Selene Mini, a state-of-the-art small language model-as-a-judge (SLMJ).

Over the last year or so, I’ve been working on evaluating large language models’ capabilities, especially from a safety perspective.

Google Deepmind recently released this paper: Mixture-of-Depths: Dynamically allocating compute in transformer-based language models.

The following is a crosspost from the alignment forum.

The below is a cross-post from the alignment forum.

The full write-up of my dissertation is now public here.

Abstract: "In many situations, given a set of observations, we would like to find the factors which cause or influence the data we observe.

Generally speaking, the performance of neural networks on various tasks scales with their depth.

Do flat minima generalise better?

An investigation of transformers' and RNNs' ability to model long-term dependencies through the lens of probabilistic modelling.

This project uses Gaussian processes (GPs) as surrogate models for accurate climate forecasting.

The full write-up of my undergraduate thesis is available here.