原帖引用 · AI 翻译
🧵3/n 已有10多家公司在高管猎聘、客户体验、金融服务和AI智能体平台领域使用Thorsten-4；一家多策略对冲基金还开始依据它对财报电话会议的解读，交易一个规模为5000万美元的专门投资组合。
多家排名前10的高管猎聘公司也将它对领导层访谈的解读与自身评估进行对照，并予以确认。
🧵2/n. 官方网站 - https://t.co/71q9knXri3
如今，AI正像心理学家一样学习心理学：连续多年观察同一批人。
Thorsten-4可以通过millionways Platform、API、MCP（模型上下文协议，一种将AI智能体连接到外部工具的标准方式）或自行托管的部署方式，接入企业已在运行的模型、智能体和AI产品，因此无需替换现有产品。
在已完成的企业试点中，结合Thorsten-4的GPT在判断客户意图方面胜过单独使用的GPT。
原文
🧵2/n. Official Site - https://t.co/71q9knXri3 AI is now learning psychology the way psychologists do, by watching the same people for years. Thorsten-4 plugs into the models, agents and AI products companies already run, through the millionways Platform, an API, MCP (Model Context Protocol, a standard way to hook AI agents up to outside tools) or a self-hosted setup, so nothing gets replaced. In completed enterprise pilots, GPT paired with Thorsten-4 beat GPT alone at reading customer intent.
这次发布太出色了，这是一种截然不同的AI。
@millionwaysai今天推出了Thorsten-4，这是一种能够解读人们动机的AI
每家AI公司都用同样的互联网数据训练模型，而互联网上并没有记录人们为何会那样行事。
因此，如今负责销售电话、求职面试和客户服务的AI智能体不断误读人们，而每次误读都会让一笔交。
> Thorsten-4建立在15年以上的心理学研究之上，这项研究早在ChatGPT出现之前就已开始，
> 50多名受过训练的心理学家在4年里反复访谈了7000多人（从8岁儿童到亿万富翁），
> 对这些谈话中超过3500万个词进行了人工标注，并将模型的预测与人们实际采取的行动进行核对。
它是一个大型心理学模型，让AI能够读懂言语背后的人，以经验证的90%准确率预测其动机、决策方式和可能的反应。
如今，AI智能体负责销售电话、求职面试和谈判，但它们察觉不到决定这些对话如何收场的犹豫和抵触，比如潜在客户说“听起来很棒”时背后的疑虑。
大语言模型旨在理解文字，而非理解人；在追踪一个人的想法和感受如何随时间变化方面，10个领先的AI模型比人类低约45%。
它们也很容易退让：当用户提出异议时，领先的AI模型有46%的概率会改变原本正确的答案。
Thorsten-4会解读企业已有的对话（会议、访谈、电子邮件、聊天记录和客服通话），根据50项行为和心理特质为每个人评分，展示其行为动力、决策方式以及在压力下的反应。
它的训练数据无法从互联网上抓取，因为50多名受过训练的心理学家在4年里反复访谈了7000多人，并对这些谈话中超过3500万个词进行了人工标注。
随后，团队将模型的预测与成熟的心理学测试结果，以及这些人在数年间的实际行为进行核对。
每项解读都可解释，并可追溯到支持它的证据；当用户提出异议时，Thorsten-4也会坚持自己的解读。
企业将它接入现有的AI工具，让智能体知道何时该推进、何时该暂停，以及如何调整应对方式。
🧵1/n
https://t.co/pobxIhjhtP
原文
Brilliant release and this is such a different kind of AI. @millionwaysai launched Thorsten-4 today, AI that reads people’s motives Every AI company trains on the same internet, and the internet doesn’t record why people do what they do. So the AI agents now running sales calls, job interviews and customer service keep misreading people, and each misread costs a dea. > Thorsten-4 is built on 15+ years of psychology research that started long before ChatGPT, > 50+ trained psychologists interviewed 7,000+ people repeatedly over 4 years (from an 8-year-old to billionaires), > hand-tagged 35M+ words from those conversations, and checked the model’s predictions against what people actually did. It’s a Large Psychology Model that lets AI read the person behind the words, predicting their motives, decision style and likely reactions with 90% validated accuracy. AI agents now run sales calls, job interviews, and negotiations, but they miss the hesitation and pushback that decide how those conversations end, like the doubt behind a prospect’s “sounds great”. LLMs were built to read words, not people, and 10 leading AI models fall about 45% short of humans at tracking how a person’s thoughts and feelings change over time. They also cave easily, since leading AI models flip a correct answer 46% of the time when a user pushes back. Thorsten-4 reads the conversations companies already have (meetings, interviews, emails, chats and support calls) and scores each person on 50 behavioral and psychological traits, showing what drives them, how they decide and how they react under stress. Its training data can’t be scraped off the internet, because 50+ trained psychologists interviewed 7,000+ people again and again over 4 years and hand-tagged 35M+ words from those conversations. The team then checked the model’s predictions against established psychology tests and against what those people actually did over several years. Every read is explainable and traces back to the evidence behind it, and Thorsten-4 holds its read when a user pushes back. Companies plug it into the AI tools they already use, so their agents know when to push, when to pause and how to adapt. 🧵1/n https://t.co/pobxIhjhtP