MATS Fellow:
Brendan Halstead, Alex Kastner
Authors:
Eli Lifland, Brendan Halstead, Alex Kastner, Daniel Kokotajlo
Citations
Abstract:
This website presents the AI Futures Model (Dec 2025 version), following up on the timelines and takeoff models we published alongside AI 2027. Predicting superhuman AI capabilities inherently requires much intuition and guesswork, but we've nonetheless found quantitative modeling to be useful.
Gradient Routing Localizes and Removes Unintended Behaviors in RL
Authors:
Jake Ward, Shawn Hu, Aria Wong, Nathan Hu, Alex Cloud
Date:
December 9, 2026
Citations:
Uncovering Hidden Propensities in Language Models via Limited-Parameter Finetuning
Authors:
Boyd Kane, Jo Jiao, Elizabeth Donoway, Alex Cloud
Date:
December 7, 2026
Citations: