一家初创公司结束隐身模式,推出高度个性化 AI
OpenAI 的 ChatGPT 会记住用户的细节以及他们查询的内容,而 Anthropic 的 Claude Code 则利用其“自动记忆”功能记录用户的偏好和反馈。一家新创公司认为,AI 模型可以变得更加个性化。
First Person Labs 由两名斯坦福人工智能实验室(该大学下属的一个研究机构)的博士生于七个月前创立,正在开发让“用户模型”成为可能的技术——“用户模型”指的是基于个人数据训练的、更个性化的 AI 模型和智能体。这家初创公司于周二走出隐身模式,已在由 Andreessen Horowitz 基础设施团队领投的一轮融资中筹集约 1000 万美元。
“你与之交谈的任何界面都了解你,”该公司联合创始人兼 CEO Ken Liu 表示,并补充说公司的技术“就像一位传记作者——一个跟随你左右、看到一切的人。”
译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。
查看英文原文(A Startup Emerges From Stealth With Highly Personalized AI)
OpenAI’s ChatGPT remembers details of its users and what they look up, while Anthropic’s Claude Code uses its “auto memory” to take notes on users’ preferences and feedback. A new startup thinks AI models can get even more personalized.
First Person Labs, founded seven months ago by two PhD students in the Stanford Artificial Intelligence Laboratory, a research institute at the university, is developing tech to make “user models,” the term for more personalized AI models and agents trained on an individual’s data. The startup is coming out of stealth Tuesday and has raised around $10 million in a funding round led by Andreessen Horowitz’s infrastructure team.
“Any interface you talk to knows you,” Ken Liu, the company’s co-founder and CEO, said, adding that the company’s tech is “like a biographer—someone that follows you around and sees everything.”
正文保留英文原文,标题与摘要由机器翻译。
原文发布于 The Information AI(A Startup Emerges From Stealth With Highly Personalized AI),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。