# 3–40% Personalization Gains Without Any New Data or External Judges

- slug: 3-40-personalization-gains-without-any-new-data-or-external-judges
- date: 2026-03-23
- category: Artificial Intelligence

A Stanford PhD student has built a method that lets language models improve themselves through personalization — with no additional labeled data, no external judge, and no verifiable rewards.

---