Researcher Questions Asking LLMs to Explain Their Own Reasoning

rajiinio · x · 2026-09-01

AI researcher Rajiinio expressed skepticism about studies that ask large language models to "explain their own reasoning." He compared the practice to asking a five-year-old to explain itself and taking the response seriously, implying that LLM self-explanations are often unreliable or logically unsound.

Original post →

More from Safety

Safety channel →