Foom
  • About
Sign in Subscribe

Mordechai Rorvig

Mordechai Rorvig

Analysis

Is research into recursive self-improvement becoming a safety hazard?

One of the earliest speculations about machine intelligence was that, because it would be made of much simpler components than biological intelligence, like source code instead of cellular tissues, the machine would have a much easier time modifying itself. In principal, it would also have a much easier time improving

By Mordechai Rorvig 30 Jan 2026

News

Language models resemble more than just language cortex, show neuroscientists

In a paper presented in November 2025 at the Empirical Methods in Natural Language Processing (EMNLP) conference, researchers at the Swiss Federal Institute of Technology (EPFL), the Massachusetts Institute of Technology (MIT), and Georgia Tech revisited earlier findings that showed that language models, the engines of commercial AI chatbots, show

By Mordechai Rorvig 13 Jan 2026

Q&A

The moral critic of the AI industry—a Q&A with Holly Elmore

An interview with Holly Elmore, a leading proponent of a non-technical solution to the existential risks of AI technology.

By Mordechai Rorvig 26 Dec 2025

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.

By Mordechai Rorvig 12 Dec 2025

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

By Mordechai Rorvig 29 Nov 2025

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,

By Mordechai Rorvig 14 Nov 2025

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

By Mordechai Rorvig 07 Nov 2025

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

By Mordechai Rorvig 31 Oct 2025

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

By Mordechai Rorvig 30 Oct 2025
Foom
  • Sign up
Powered by Ghost

Covering the latest research on making AI go well