TL;DR * We steer reasoning models by editing their chain of thought mid-generation, inserting steering text that redirects the model’s reasoning. * We compared several approaches and found that the simplest method, randomly inserting steering text, generally works best. * We evaluated this across five alignment-relevant settings: harmful compliance, blackmail,...
This is my application to Neel Nanda's Summer 2026 MATS stream. I'm also posting it here on LessWrong. Executive Summary Problem When LLMs are explicitly given an option to bail from a conversation, they sometimes do. But is this because models are experiencing genuine discomfort and we should thus be...
Most practical control over LLM behavior comes from prompting, because prompts are easy to edit and LLMs have been explicitly trained to follow them. However, this only provides a starting point for the model's generation:... (read 1262 more words →)
LLMs can be evaluation-aware. They may behave differently when they detect they are being tested. This matters because a model can look aligned on evaluations while behaving differently in deployment.
Tim Hua et al. study this by training a “model organism” to behave differently in evaluation vs deployment, and to treat “Wood Labs”... (read more)
This is my application to Neel Nanda's Summer 2026 MATS stream. I'm also posting it here on LessWrong.
When LLMs are explicitly given an option to bail from a conversation, they sometimes do. But is this because models are experiencing genuine discomfort and we should thus be concerned about their welfare? In investigating this, Ensign et al. created BailBench, a synthetic benchmark, and measured bail rates on real chats, built a taxonomy of bail situations, and tried to disentangle the difference between bail and refusal.
This motivates a mechanistic follow-up. What internal features causally drive bail, and do they support a welfare interpretation?