EPISODE · Aug 19, 2026 · 11 MIN
The Wug Test for AI
from Inside the Black Box: Cracking AI and Deep Learning · host Arshavir Blackwell, PhD
This episode explores a modern twist on Jean Berko’s famous wug test, comparing how large language models handle made-up verbs versus familiar ones. It digs into tokenization, internal feature probes, and why neural networks seem to approximate grammar through probabilistic patterns rather than clean symbolic rules.
Embed this episode
Ready to play
The Wug Test for AI
No transcript for this episode yet
Similar Episodes
Feb 4, 2026 ·18m