Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models. The team shared concrete examples and stress tests of an early method to reduce scheming.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
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.
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.
arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
arXiv:2607. 29008v1 Announce Type: cross Abstract: Modern opaque AI models prize performance over interpretability, which makes testing difficult.