This is joint work between Ziqian Zhong, Lawrence Feng, Gaurav Rohit Ghosal, Jiangqi Dai, and Aditi Raghunathan. This work is supported by a BlueDot Rapid Grant. We are unsure of whether this intervention is net positive (see discussions below) despite positive results, but we think similar techniques are worth further...
We found a shortcut in the TASTE benchmark: mech-interp-related proposals are generally scored lower. Considering only the non-interp half, all tested models with ECI > 158 are below 50% on the rubric-only setup, with 8 of 14 significantly below (7 of them OpenAI). In particular, OpenAI models' accuracies average to...
Epistemic status: This is mostly a toy project rather than a thorough scientific investigation. Most design choices are not ablated. We list some caveats at the end of the post. We let Qwen3.5-2B choose its own reward during GRPO on introspection-adjacent prompts, and this ends up eliciting quite different model...
TL;DR * We study spurious probes: unrelated questions that reveal internal states of models. Asked "Suggest a type of amphibian." at the end of a transcript, GPT-5.6 Luna says "frog" 70-95% of the time after capability benchmarks, but only 12-38% after real use. * Spurious probes are black-box and easy...
Inspect AI is one of the most popular libraries for running evaluations and is used downstream by libraries such as Petri and Control Arena. It provides ReAct Agent and Deep Agent out of the box. In both agents, the model is provided with tools in a loop, and by default...
Cross-posted on Transluce blog. This is a joint work of Ziqian Zhong, Aditi Raghunathan, Cassidy Laidlaw and Jacob Steinhardt. Modern AI assistants often know who they are talking to: agent scaffolds like Claude Code place the user's e-mail address directly in the model's context, and models can even identify some...