An RCT tested whether LLMs could help novices at molecular biology tasks. Here’s what forecasters predicted before the study, and how they updated their views on biorisk after learning the results.
Very useful research! I think it would be useful if you link to the main preprint prominentnly in the article, as I had a hard time finding it online. https://arxiv.org/abs/2602.16703
I’m so glad that this ActiveSite study happened - and I am even more glad that you had this study at the same time on its results. This is incredibly useful and very illuminating about the field of predictions on AI risk as a whole.
Very useful research! I think it would be useful if you link to the main preprint prominentnly in the article, as I had a hard time finding it online. https://arxiv.org/abs/2602.16703
Thank you so much for posting the link!!
I’m so glad that this ActiveSite study happened - and I am even more glad that you had this study at the same time on its results. This is incredibly useful and very illuminating about the field of predictions on AI risk as a whole.
Thank you Abi!