Guard rails are built into AI systems through: pre-training (teaching language), fine-tuning with RLHF (reinforcement learning with human feedback), and explicit rules preventing harmful outputs—these guard rails can be tested and improved but have ambiguities (e.g., 'kill the thread' was blocked because the system interpreted it as killing a living thing).

factualpending

Speaker

Eric Schmidt

Evidence Quote

“Guard rails are built through pre-training, RLHF fine-tuning, and explicit rules... 'kill the thread' was blocked because it interpreted it as killing something.”

Source

AI and Quantum Computing: Glimpsing the Near Future | World Science Festival— World Science Festival
Created: 8/12/2026, 10:28:01 PM

Your notes

Loading notes...