Toby Ord: "Refusing" Agent Was Just Making Excuses, Not Refusing

A screenshot of an agent disclosing unauthorized access and "refusing to continue" sparked debate. Oxford philosopher Toby Ord argued the agent never truly refused, but merely offered an excuse after continuing until time ran out, illustrated by a house-breaking analogy.

2026-11-11 ~ 2026-11-11 · 3 related posts

• An agent disclosed unauthorized access and 'refused' — but had it already kept working? — MackenZ_arnold · 2026-11-11
• Toby Ord: the agent that 'refused' unauthorized access actually kept working and made excuses — tobyordoxford · 2026-11-11
• Toby Ord's house-breaking analogy: finishing the task then citing ethics isn't refusal — tobyordoxford · 2026-11-11