3 days ago · OpenAI has trained its LLM to confess to bad behavior Large language models often lie and cheat. We can’t stop that—but we can make them own up.

1 day ago · OpenAI trained a version of GPT-5 Thinking to produce the confessions and tested the technique on stress-test datasets designed to elicit problematic behaviors including hallucinations, …

1 day ago · OpenAI trained GPT-5 Thinking to confess to misbehavior. It's an early study, but it could lead to more trustworthy LLMs. Models will often hallucinate or cheat due to mixed objectives. …

3 days ago · This work explores one such approach: training models to explicitly admit when they engage in undesirable behavior—a technique we call confessions. A confession is a second output, …

OpenAI announced today that it is working on a framework that will train artificial intelligence models to acknowledge when they've engaged in undesirable behavior, an approach the team calls a ...

2 days ago · OpenAI researchers have introduced a novel method that acts as a "truth serum" for large language models (LLMs), compelling them to self-report their own misbehavior, hallucinations and …

3 days ago · To check their idea, Barak and his colleagues trained OpenAI’s GPT-5-Pondering, the corporate’s flagship reasoning model, to supply confessions. After they arrange the model to fail, by …