# Can We Reliably Align an AGI to Stop an Unaligned AGI by Eliezer S. Yudkowsky > “What is the fastest way to reliably align a powerful AGI around the safe performance of some limited task that is potent enough to save the world from unaligned AGI?” > **— Eliezer S. Yudkowsky**, *2018 Edge Annual Question, question* ## Sources and Context - **Original Edge response:** [The Last Question — Eliezer S. Yudkowsky](https://www.edge.org/response-detail/27658) — Eliezer S. Yudkowsky's question in the 2018 Annual Question collection, posed rather than asserted as a conclusion. The Edge response page is the publication record for this exact question. - **Local archival entry:** [[research/Edge 2018 Full Quotation Curation|Edge 2018 Full Quotation Curation]] (EDGE2018-086). ## Related Articles and Collections - **Collection:** [[collections/Edge|Edge]] - **Collection:** [[collections/Machine Succession|Machine Succession]] - **Article:** [[articles/Modern Artificial Intelligence in the 1970s|Modern Artificial Intelligence in the 1970s]] - **Article:** [[articles/Cyber-Physical Lessons from Imperial Beekeeping|Cyber-Physical Lessons from Imperial Beekeeping]] - **Article:** [[articles/The Last Migration Will Not Be Human|The Last Migration Will Not Be Human]] ## Related Topics - [[wiki/Alignment Problem|Alignment Problem]] ## Share on Social Media ``` “What is the fastest way to reliably align a powerful AGI around the safe performance of some limited task that is potent enough to save the world from unaligned AGI?” — Eliezer S. Yudkowsky, 2018 Edge Annual Question https://bryantmcgill.com/simple-reminders-eliezer-yudkowsky-we-reliably-align-agi-stop ```