Felix J. Binder, James Chua, Tomek Korbak, Henry Sleight, John Hughes, Robert Long, Ethan Perez, Miles Turpin, Owain Evans · 2025 · ICLR 2025 Read the paper Models trained to predict their own behavior do better at it than other models trained on the same data, which is evidence of privileged self-access on simple tasks. Questions it bears on How well can LLMs introspect