Use Large Language Models (LLMs) for reasoning, and orchestrate multiple large models for accomplishing sophisticated tasks

Chatgtp like interfaces will make generative vastly more accessible

Everything, everywhere all at once...

LERF: Language Embedded Radiance Fields

Grounding CLIP vectors volumetrically inside a NeRF allows flexible natural language queries in 3D

abs: https://buff.ly/42nMomv project page: https://buff.ly/42nMpXB

Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

demo: https://lnkd.in/eX8fKsiu

The surprising ease and effectiveness of AI in a loop

https://interconnected.org/home/2023/03/16/singularity

build a system called Visual ChatGPT, incorporating different Visual Foundation Models, to enable the user to interact with ChatGPT by 1) sending and receiving not only languages but also images 2) providing complex visual questions or visual editing instructions that require the collaboration of multiple AI models with multi-steps. 3) providing feedback and asking for corrected results

abs: https://buff.ly/3JqVnft

Jina AI have created AgentChain, it can help you automate a wide range of tasks, across different modalities, has access to internet information and can also call you! Check out what else it can do here:

GitHub - jina-ai/agentchain: Use Large Language Models (LLMs) for reasoning, and orchestrate multiple large models for accomplishing sophisticated tasks