Abstract: Implementations are described herein for using the information about user engagement with large language model (LLM) output as a subsequent input into an LLM, so that the LLM is able to provide, for rendition on one or more output devices, a subsequent output that is tailored to the user. In various implementations, based on one or more input device signals, a user engagement event with an element of a first LLM output generated using a LLM and rendered using one or more output devices may be detected. Additional information about the element of the first LLM output may be captured and used to generate at least part of a subsequent input prompt for the LLM. The subsequent input prompt may be processed using the LLM to generate a subsequent LLM output for rendition on one or more of the output devices.

Abstract: Implementations set forth herein relate to a graphical user interface (GUI) element that can be manipulated at an interface to indicate a particular object and/or feature of interest to be considered when providing generative output for a separate user request. One or more GUI elements can be provided at a display interface, such as a touch display panel and/or virtual or augmented reality display interface, thereby allowing the GUI elements to be associated with rendered and/or tangible objects. When a user interacts with a GUI element, the GUI element can exhibit responsive behavior that is based on features of the interaction and/or other features of a particular object. When an object of interest is identified, processing can be performed to identify information about the object, and this information can then be utilized to facilitate provisioning of a generative output that is responsive to a separate user request.

Abstract: Implementations are described herein for using the information about user engagement with large language model (LLM) output as a subsequent input into an LLM, so that the LLM is able to provide, for rendition on one or more output devices, a subsequent output that is tailored to the user. In various implementations, based on one or more input device signals, a user engagement event with an element of a first LLM output generated using a LLM and rendered using one or more output devices may be detected. Additional information about the element of the first LLM output may be captured and used to generate at least part of a subsequent input prompt for the LLM. The subsequent input prompt may be processed using the LLM to generate a subsequent LLM output for rendition on one or more of the output devices.

Abstract: Implementations set forth herein relate to a graphical user interface (GUI) element that can be manipulated at an interface to indicate a particular object and/or feature of interest to be considered when providing generative output for a separate user request. One or more GUI elements can be provided at a display interface, such as a touch display panel and/or virtual or augmented reality display interface, thereby allowing the GUI elements to be associated with rendered and/or tangible objects. When a user interacts with a GUI element, the GUI element can exhibit responsive behavior that is based on features of the interaction and/or other features of a particular object. When an object of interest is identified, processing can be performed to identify information about the object, and this information can then be utilized to facilitate provisioning of a generative output that is responsive to a separate user request.

Abstract: Implementations are described herein for using the information about user engagement with large language model (LLM) output as a subsequent input into an LLM, so that the LLM is able to provide, for rendition on one or more output devices, a subsequent output that is tailored to the user. In various implementations, based on one or more input device signals, a user engagement event with an element of a first LLM output generated using a LLM and rendered using one or more output devices may be detected. Additional information about the element of the first LLM output may be captured and used to generate at least part of a subsequent input prompt for the LLM. The subsequent input prompt may be processed using the LLM to generate a subsequent LLM output for rendition on one or more of the output devices.