大模型是目前智能体大脑的最优选择，因为大模型的万亿参数压缩了人类积累的海量知识，拥有强大的模式识别和生成能力，是处理包括语言在内的多种非结构化数据的万能接口，拥有不错的泛化能力构成处理各类任务的基础。而以OpenAI o1/DeepSeek R1为代表的新一代推理模型为智能体的发展进一步助推：加强的推理能力带来更强的任务分解和规划，更好地自检和纠错，也令智能体对工具的使用可以更加准确。
"It is interesting that a lot of the things that we are addressing directly go to the points they raised in their report," Isaacman said Friday. "I can't say we actually collaborated on it because I generally think these were all pretty obvious observations."
，这一点在谷歌浏览器【最新下载地址】中也有详细论述
Updated Category: Information Technology
Last May, I wrote a blog post titled As an Experienced LLM User, I Actually Don’t Use Generative LLMs Often as a contrasting response to the hype around the rising popularity of agentic coding. In that post, I noted that while LLMs are most definitely not useless and they can answer simple coding questions faster than it would take for me to write it myself with sufficient accuracy, agents are a tougher sell: they are unpredictable, expensive, and the hype around it was wildly disproportionate given the results I had seen in personal usage. However, I concluded that I was open to agents if LLMs improved enough such that all my concerns were addressed and agents were more dependable.