← Toutes les offres
LC

Protecting AI, Perspectives of Religious Scholars, and Can We Trust AI Self-Reports? — Digital Minds Newsletter #5

Lucius Caviola

Global
Publié le 16 novembre 2026

Description du poste

Welcome back to the Digital Minds Newsletter, your curated guide to the latest developments in AI consciousness, digital minds, and AI moral status. We’re hoping to bring you updates more frequently, starting with this edition! If you enjoy this newsletter, please consider sharing it with others who might find it valuable, and send any suggestions or corrections to digitalminds@substack.com. Ria, Bradford, Will, and Lucius In this edition: • Highlights• Field Developments• Opportunities and Events• Selected Reading, Watching, and Listening• Press and Discourse• A Deeper Dive by Area1. HighlightsSelected ResearchAssessing AI self-reportsIn a preprint on arXiv, David Atkinson, Dillon Plunkett, and David Bau investigate how to distinguish accurate introspective AI self-reports from plausible confabulation. Researchers trained models to make choices on behalf of fictional characters. Some models could then report the characters’ preferences, despite receiving no training on that task. To assess accuracy, the researchers compare these reports with preferences inferred from the models’ actual choices. The paper links report accuracy to the location of preference information within the model, with greater accuracy correlating with that information being encoded in earlier layers. The authors suggest that this might allow existing mechanisms in later layers to use that information when generating reports. A possible “mechanistic signature” for identifying reliable self-reports, without relying on their contents, was identified – models that reported preferences accurately used more similar internal processes when describing those preferences and acting on them. The method found differences between models that reported their preferences accurately and those that did not, but cannot yet reliably assess individual model self-reports. Whether it works for more complex claims about models’ internal states and in more naturalistic settings remains an open question. Comment: A maj