OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI honesty, transparency, and trust in model outputs.
Summary generated by The Flow from the publisher's feed. The full article lives at OpenAI Blog.
OpenAI’s new research explains why language models hallucinate. The findings show how improved evaluations can enhance AI reliability, honesty, and safety.
Learn how OpenAI’s Model Spec serves as a public framework for model behavior, balancing safety, user freedom, and accountability as AI systems advance.
In this post we’ll outline new OpenAI research in which agents develop their own language.
arXiv:2607. 14791v1 Announce Type: new Abstract: Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour.
arXiv:2608. 08881v1 Announce Type: new Abstract: The current work developed seven Retrieval-Augmented Generation (RAG) models based on leading deception theories and compared how deception judgments were made relative to baseline models.
OpenAI introduces CoT-Control and finds reasoning models struggle to control their chains of thought, reinforcing monitorability as an AI safety safeguard.