Check out our paper on whether first-price auctions can efficiently allocate queries among strategic AI agents (in a decentralized serving-time market): arxiv.org/abs/2610.20587

Show Post

We further validated LIDS on protein language model (PLM) oracles in silico. It is very fast. Here, LIDS can find the optimum in 2 experimental rounds (median), while individual synthesis alternatives need an order of magnitude more experiments.

Show Post

Assuming a generous attention span re: eager, I think it's useful to give stuff which make the point incidentally. For example: Warwick's Masters of Theory. The material is technical and these are people doing mathematical physics, and are at the top of their game. And yet, as you move through the

Show Post

Introducing: continuous variational synthesis 📄 jurabio.com/s/cvs.pdf We’re pleased to announce a new advance in our ability to synthesize generative model-designed DNA sequences at petascale.

Show Post

This already uses old school ML. The trial is for V940, which was tested on around 1300 patients who had the cancer surgically removed. It is a personalized mRNA-based cancer vaccine. So it's not really the usual molecular drug, you end up producing a different medicine for every person's tumour.

Show Post