In these research notes, I will share some CoT traces from lightly fine tuned checkpoints of Kimi K2.5 that may be examples of load-bearing obfuscation within the internal reasoning outputs of the model. These are notes and collected model outputs from a project that I have been working on haphazardly...
[For MATS mentors: please see here for research updates on my ongoing CoT obfuscation model organism project] Measuring out-of-context Schelling coordination capabilities in large language models. Overview This is my first foray into AI safety research, and is primarily exploratory. I present these findings with all humility, make no strong...
How might we best design experiments to measure Schelling coordination capabilities? A side project building a Schelling coordination eval has led to a role as an AI Safety researcher - this work will officially begin in a month or so. I have been hesitant to post here or share my...