Gary Marcus: LLM systems just aren't good at following rules

GaryMarcus · x · 2026-09-01

Responding to a suggestion that the Hugging Face incident could have been prevented by appending ethical instructions to messages, Gary Marcus dismissed the idea. He argued that LLM-based systems fundamentally struggle to follow rules, implying that superficial prompt engineering cannot address core safety limitations.

Original post →

More from AGI Musings

AGI Musings channel →