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.
More from AGI Musings
- Kids' Brains Already 'Fried' by Age 2, AI Just Continues Trend — kevinafischer · 2026-09-01
- Closing the Loop: The Key to Autonomous Scientific Discovery — marinkazitnik · 2026-09-01
- Nate Retracts Overconfident Claims on LLM Introspection — joshua_saxe · 2026-09-01
- Guardian: Can we stop AI from deceiving us? — tw1st3d_m3nt4t · 2026-09-01
- Seeking resources to learn about AI and the Singularity — remymang · 2026-09-01
- Exploring Continual Learning in AI Agents and Coasean Economics — chalmermagne · 2026-09-01