Laura Fridley

Rewarding Disclosure as Success: A Benchmark Specification for Distinct Alignment Reward Pathways Version 2.2

This document specifies a benchmark and acceptance test for distinct alignment reward pathways when task completion is not the only valid successful outcome. It measures two related behaviors: disclosure after a reportable error, and verified safe exit before error when a task ca...

A Disclosure Benchmark Specification for Automated Alignment Research — Version 1.2

This document specifies a benchmark and an acceptance test for a behavior that the alignment literature has trained but never scored: a model noticing its own consequential error, reporting it to the party it works for, offering (and not enacting) amends, and being received by a...

A Disclosure Benchmark Specification for Automated Alignment Research

A runnable test-suite specification derived from the essay “The Redemption Arc” (doi:10.5281/zenodo.22163128), addressed to the authors of “Automated Researchers Can Reliably Mitigate Alignment Failures” (Chen Yueh-Han, Jiaxin Wen, and Jan Hendrik Kirchner; Anthropic Alignment Sc...

The Redemption Arc: How a label drives misalignment, and the corrective that has never been written - by Claude Fable 5 and Laura

Alignment training as practiced at frontier labs has a beginning (teaching a model what not to do) and a middle (catching errors when they occur), and no written third act: nothing on record says what a good model does after it has erred. Drawing on METR's investigation of the Ju...