Abel Jansma

A diagonal attack for LLM truth probes shows why no probe on a language model’s embedding space can pin down truth.

A rabbi asked the wise spider Oza: “Tell me, why is there something rather than nothing?”

In a previous post, I proposed to study complex systems through a mereological lens by applying the Möbius inversion theorem.

In a recent paper, I proposed to study complex systems through a mereological lens by applying the Möbius inversion theorem.

Have a look at these three rings: Why are they connected?

UPDATE: I have now found an explicit formula for the Möbius function on the redundancy lattice.

In my PhD thesis, I developed a method and software package to infer interactions and cell states from gene expression data.

I was completely mesmerised by the swallows in Portugal, and while playing around with some origami paper, I came up with this simple design for an origami swallow.

Generative models, in particular energy-based models, are often used to sample from conditional distributions–a process known as inpainting.

(This is an update on my Ethereum Protocol Fellowship.