x

LESSWRONG

LW

Dewi Gould — LessWrong

Dewi Gould

Dewi Gould

Message

103

1y

Dewi Gould

103

1y

Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models

by Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask, Twm Stone, josh-hills, and Ida Caspary

(see full author list at the end) About a year ago, METR showed that the length of tasks frontier models can reliably complete doubles every few months. A related safety-relevant question is this: what length of tasks can models complete without any chain of thought (CoT)? We investigate in our...

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

by harrymayne, Justin kang, Dewi Gould, and noahys

This is a summary of our new paper. TL;DR: Existing faithfulness metrics are not suitable for evaluating frontier LLMs. We introduce a new metric based on whether a model's self-explanations help people predict its behavior on related inputs. We find self-explanations encode valuable information about a model decision-making process (though...