Mechanistic Interpretability · EP 4 · Jul 23, 2026

AI's Hidden Modes: What's Really Going On Inside

Name: AI's Hidden Modes: What's Really Going On Inside
Uploaded: 2026-07-23T19:13:12.616Z
Description: The newest research in Mechanistic Interpretability, explained.

This week in Mechanistic Interpretability

Papers covered

Sycophancy has secret modesarXiv:2607.20146
Topology maps robustness geometricallyarXiv:2607.20185
Fuzzy rules beat black boxes clearlyarXiv:2607.20277
AI scores rehab with phase awarenessarXiv:2607.20237
Labels hide human disagreementarXiv:2607.20149
LLM writing quality compared directlydoi:10.31127/tuje.1838765

Your field, every week

Get this for your own field.

Sciport turns the newest papers in your corner of the literature into a short weekly video like this one — auto-curated, delivered to your inbox. First episode’s on us.

Generate your first video →