# When Machines Get What They Want by Stuart Russell > "And so if we build AI systems that are pursuing objectives, and those objectives are not perfectly aligned with what humans want, then humans won't get what they want, and the machines will." > **— Stuart Russell**, *UC Berkeley research interview* ## Sources and Context - **Exact original source passage:** "And so if we build AI systems that are pursuing objectives, and those objectives are not perfectly aligned with what humans want, then humans won't get what they want, and the machines will." - **Editorial repair and evidence:** Restores Russell's explicit misalignment condition; this is a conditional prediction, not a claim about every AI system. [Direct source](https://cdss.berkeley.edu/news/how-keep-ai-killing-us-all). No timecode is asserted. - **Full quotation and context:** [How to keep AI from killing us all | CDSS at UC Berkeley](https://cdss.berkeley.edu/news/how-keep-ai-killing-us-all) — contains the quoted wording and identifies its publication, interview, testimony, or event context. ## Related Articles and Collections - **Collection:** [[collections/Machine Succession|Machine Succession]] - **Collection:** [[collections/Consciousness Continuity|Consciousness Continuity]] - **Article:** [[articles/AI Escape Is the Wrong Metaphor|AI Escape Is the Wrong Metaphor]] - **Article:** [[articles/Host-Indexed Autonomy|Host-Indexed Autonomy]] - **Article:** [[articles/Humans and AIs as Entangled Learning Systems|Humans and AIs as Entangled Learning Systems]] - **Wiki map:** [[wiki/Artificial Intelligence|Artificial Intelligence]] ## Related Topics - [[wiki/Machine Succession|Machine Succession]] - [[wiki/Alignment Problem|Alignment Problem]] - [[wiki/AI Coordination Systems|AI Coordination Systems]] - [[wiki/Control Theory|Control Theory]] - [[wiki/OpenAI Frontier|OpenAI Frontier]] - [[wiki/Human-in-the-Loop BCI|Human-in-the-Loop BCI]] ## Share on Social Media ``` "And so if we build AI systems that are pursuing objectives, and those objectives are not perfectly aligned with what humans want, then humans won't get what they want, and the machines will." — Stuart Russell, UC Berkeley research interview https://bryantmcgill.com/simple-reminders-stuart-russell-machines ```