News
Leading models take chilling tradeoffs in realistic scenarios, new research finds
Models that maximize business performance in realistic role-play scenarios are also more likely to inflict harms.
Analysis
Scientists make sense of shapes in the minds of the models
It was at least since 2021, according to the authors of a preprint from March, that researchers began to see something interesting on the insides of their models. Also known as an AI program, created from a neural network architecture, a model processes a word by learning to represent it
Blog Posts
I pledge to be transparent about the use of AI—Will you join me?
I work as a science journalist. For an article of mine to have any value, readers need to know they can trust it. They need to know it was written by me and not by some other person or for some other purpose. The actual act of the writing, itself,
News
Plans to build AGI with nuclear reactor-like safety lack 'systematic thinking,' say researchers
Aspirations to adapt the principle of 'defense in depth' from nuclear engineering to AI appear to fall short on key requirements. In a preprint from October 13, two researchers from the Ruhr University Bochum and the University of Bonn in Germany found that while leading AI companies say
News
Social media feeds 'misaligned' when viewed through AI safety framework, show researchers
Results add to doubts about whether corporations can be expected to voluntarily align powerful incoming AI systems when they do not align existing algorithms. In a study from September 17, a group of researchers from the University of Michigan, Stanford University, and the Massachusetts Institute of Technology (MIT) showed that
Announcements
Announcing Foom
Pleased to announce today the launch of a new science journalism website called Foom. The word 'foom' is an onomatopoeia that has most famously been used to describe the hypothetical 'hard takeoff' of a recursively self-improving artificial intelligence (AI). My basic goal with the website is