AnalysisAI Models
2 hours ago
LLMs fail to tailor math explanations to user levels
Naomi Saphra
@nsaphra.bsky.socialWaiting on a robot body. All opinions are universal and held by both employers and family. ML/NLP professor. nsaphra.net
Naomi Saphra
@nsaphra.bsky.social
How do you make LLMs actually good at explaining new math? It's like reading a badly written reference for people who already know the subject. When I ask a question, it never matches my level. If I try to rephrase to test my understanding, it just sycophantically agrees.
·
2 hours ago