arXiv:2606. 07612v1 Announce Type: cross Abstract: We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for critical safety decisions, such as model deployment and regulation.
By Vansh Gupta, Peter Nutter, Samuel Stante, Andreas Krause, Florian Tram\`er, Lukas Fluri, Xin Chen, Anna Hedstr\"om
OpenAI introduces a framework designed to track, investigate, and disclose instances of model misalignment. The framework is accompanied by six reports that document unexpected or concerning behaviors observed in their models.
How OpenAI uses chain-of-thought monitoring to study misalignment in internal coding agents—analyzing real-world deployments to detect risks and strengthen AI safety safeguards.
arXiv:2605. 29729v2 Announce Type: replace Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity.
By Victoria Krakovna, David Lindner, Lewis Ho, Sebastian Farquhar, Rohin Shah
arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.
By David Demitri Africa, Arathi Mani
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.