Abstract: In one implementation, a method of generating content is performed at a device having one or more processors and non-transitory memory. The method includes obtaining a database including a plurality of elements. The method includes generating a prompt to select one of the plurality of elements that satisfies one or more criteria regarding a topic of interest. The method includes submitting the prompt to a foundational model trained on a training dataset. The method includes receiving, from the foundational model in response to the prompt, content including a selected one of the plurality of elements.

Abstract: In one implementation, a method of displaying a virtual object is performed at a device in a physical environment, the device having a display, one or more processors, and non-transitory memory. The method includes displaying, on the display, a virtual object as a device-world-locked virtual object in a three-dimensional virtual portion of a mixed reality environment. The method includes detecting a device-world-to-physical-world transition trigger. The method includes, in response to detecting the device-world-to-physical-world transition trigger, displaying the virtual object as a physical-world-locked virtual object in a three-dimensional real portion of the mixed reality environment corresponding to at least a portion of the physical environment.

Abstract: In one implementation, a method of displaying virtual content is performed at a device in a physical environment, the device having a display, one or more processors, and non-transitory memory. The method includes detecting an object in the physical environment. The method includes determining that a spatial relationship between the device and the object satisfies one or more display criteria. The method includes, in response to determining that the spatial relationship between the device and the object satisfies the one or more display criteria, displaying, on the display, virtual content.