由北京市通州区人民政府指导，《财经》杂志、财经网、《财经智库》主办的"《财经》年会2026：预 测与战略 · 年度对话暨2025全球财富管理论坛"于12月18日至20日在北京举行，主题为"变局中的中国定 力"。 12月19日，腾讯首席科学家、Robotics X实验室主任、福田实验室主任张正友在论坛上表示，我们要从 目前的身和智割裂的拼接，强行把没有世界认知的AI塞进机器人的状态，过渡到身智融合，机器人在 与环境持续闭环交互中"身"与"智"要能动态、协同地进化，无缝地适应多变的环境，不断提升自己的能 力，涌现出真正的具身智能。 腾讯首席科学家、Robotics X实验室主任、福田实验室主任 张正友 在演讲中，张正友首先厘清了具身智能的核心概念。他指出，具身智能是相对于"离身智能"（如 ChatGPT等无身体的AI）而言，指拥有物理身体（如机器人、无人机）或虚拟身体（如数字人）的智能 体。其关键特征在于能通过主动感知、规划和控制来改变真实物理世界，并基于反馈调整策略。 张正友分析了具身智能近年来兴起的原因。具身智能是涉及多个学科的融合，包括传统机器人领域的机 械工程、自动化、嵌入式系统控制优化，还有计算机领域下 ...

Core Insights - Sora2 demonstrates advanced capabilities in predicting ChatGPT outputs and rendering HTML, blurring the lines between video generation and interactive AI [2][6] - The system can simulate interactions, generating audio responses in a ChatGPT-like manner, showcasing its ability to create coherent and contextually relevant content [4][5] - Sora2 exhibits a strong understanding of physical phenomena, such as light refraction, without explicit prompts, indicating a high level of intelligence and information processing ability [14][18] Group 1: Sora2's Capabilities - Sora2 can generate interactive content, including video scenes and audio responses, effectively simulating a conversation with ChatGPT [4][6] - The system successfully rendered HTML code, producing results that closely match what would be seen in a real browser [7][12] - Sora2's ability to understand and simulate physical concepts, like glass refraction, was demonstrated through a practical test, impressing users with its accuracy [15][18] Group 2: Game Simulation and Information Processing - Sora2 accurately recreated elements from the game "Cyberpunk 2077," including map locations, terrain, and vehicle designs, showcasing its capability to extract and integrate key information [21][25] - Despite minor inaccuracies, Sora2's performance in simulating a side quest reflects its advanced information processing skills and understanding of complex scenarios [24][25] - There is speculation that Sora2's high-level performance may be based on training with large language models (LLMs), hinting at its potential for further undiscovered capabilities [26][27]