惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

爱范儿
爱范儿
大猫的无限游戏
大猫的无限游戏
J
Java Code Geeks
MongoDB | Blog
MongoDB | Blog
Martin Fowler
Martin Fowler
GbyAI
GbyAI
Microsoft Azure Blog
Microsoft Azure Blog
Recent Announcements
Recent Announcements
F
Fortinet All Blogs
B
Blog
U
Unit 42
B
Blog RSS Feed
D
DataBreaches.Net
Google DeepMind News
Google DeepMind News
人人都是产品经理
人人都是产品经理
腾讯CDC
量子位
酷 壳 – CoolShell
酷 壳 – CoolShell
V
Visual Studio Blog
博客园 - 聂微东
MyScale Blog
MyScale Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园 - 三生石上(FineUI控件)
Engineering at Meta
Engineering at Meta

MIT CISR

Client Challenge Client Challenge Client Challenge Client Challenge Client Challenge Client Challenge Client Challenge Client Challenge The AI Decision Matrix Designing Decision Rights for AI Designing Decision Rights for AI Decision Rights for AI Client Challenge Client Challenge Client Challenge Client Challenge Client Challenge Leveraging Digital Colleagues for Enterprise Value Teaching Case: How to Grow the Salesforce Platform Business? Client Challenge Client Challenge Minimum Viable Governance for Generative AI Client Challenge Business Models in the Agentic AI Era—Session Presentation Client Challenge Managing Digital Colleagues—Session Presentation Hands-on with AI Governance: Designing Adaptive Guardrails—Session Presentation Client Challenge Client Challenge Business Models in the Agentic AI Era—Session Presentation
Predicting Human Behavior with AI Simulations
By Benjamin S. Manning and Nick van der Meulen · 2026-06-04 · via MIT CISR
Abstract

Today, many companies are using generative AI to streamline processes, summarize data, and assist with coding, among other things. They are exploring how companies can embed agents in processes (leading to changes in business models) and what it means to have digital colleagues, all based on LLMs—large language models that are trained on massive amounts of human-generated data. One of the interesting things companies can use LLMs for is to simulate how people (customers, competitors, partners) might behave in markets or strategic settings. The challenge, though, is that these simulations are inconsistent; sometimes they look strikingly human, and other times they fail badly. In this video presentation, Ben focuses on methods for making AI simulations more reliable, and on experimental evidence showing when and why those methods work.

Why can't I view this research?

Video presentations from MIT CISR Hot Topic events are available only to logged-in members and attendees of the event.

See the list of MIT CISR members

MIT CENTER FOR INFORMATION SYSTEMS RESEARCH (CISR)

Founded in 1974 and grounded in MIT's tradition of combining academic knowledge and practical purpose, MIT CISR helps executives meet the challenge of leading increasingly digital and data-driven organizations. We work directly with digital leaders, executives, and boards to develop our insights. Our research is funded by member organizations that support our work and participate in our consortium. 

ANZ Banking Group (Australia)

Banco Bradesco S.A. (Brazil)

Commonwealth Superannuation Corp. (Australia)

Cuscal Limited (Australia)

DBS Bank Ltd. (Singapore)

Doosan Corporation (Korea)

Fomento Economico Mexicano, S.A.B., de C.V.

Mater Private Hospital (Ireland)

National Australia Bank Ltd.

Nomura Holdings, Inc. (Japan)

Nomura Research Institute, Ltd. Systems Consulting Division (Japan)

Novo Nordisk A/S (Denmark)

Pentagon Federal Credit Union

Principal Life Insurance Company

Reserve Bank of Australia

Scentre Group Limited (Australia)

Schneider Electric Industries SAS (France)

Tabcorp Holdings (Australia)

Telstra Limited (Australia)

Terumo Corporation (Japan)