"World of DaaS" podcast

The LM Brief: The Syntax Illusion

05/12/2025
0:00
15:06
Reculer de 15 secondes
Avancer de 15 secondes

This week’s World of DaaS LM Brief: MIT’s new research reveals how large language models can be fooled by their own grammar. By prioritizing sentence structure over sense, these systems risk producing confident but misleading outputs—and even ignoring built-in safety rules. 

Listen to this short podcast summary, powered by NotebookLM.

D'autres épisodes de ""World of DaaS""