How does OpenAI Operator work under the hood? | Tech deep dive скачать в хорошем качестве

How does OpenAI Operator work under the hood? | Tech deep dive

In this video, we discuss the science behind OpenAI's Operator and other browser / computer agents, including LMMs (Large Multimodal Models), Imitation Learning and Reinforcement Learning. Relevant papers for web agents: https://arxiv.org/abs/2306.06070 (Mind2Web) https://arxiv.org/abs/2310.11441 (Set-of-Mark Prompting) https://arxiv.org/abs/2207.01206 (WebShop) https://arxiv.org/abs/2401.01614 (SeeAct) https://arxiv.org/abs/2401.13919 (WebVoyager) https://arxiv.org/abs/2303.08774 (GPT-4 Technical Report) https://arxiv.org/abs/2112.09332 (WebGPT) Relevant blogposts: https://openai.com/index/computer-usi... https://www.anthropic.com/news/develo... More LLM deep dives:    • Discover How LLMs Work by Dissecting Llama   00:00 Intro 00:57 Demo 01:57 Other agents 03:16 Large Multimodal Models 05:38 Imitation and Reinforcement Learning 09:01 Outro