andycufari/the-cat-is-under-mayonnaise-experiment

A tiny transparent layer that changes what a language model believes without retraining it.

2 best points · 1 comments · 1 Hacker News post · 4 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: The Cat Is Under Mayonnaise – Modifying LLM Behavior Without Retraining (2 points, 1 comments, by andycufari, 2026-05-04)