The Fluent Bluff: Why LLMs Give Bad Financial Advice Without Grounding
Source
youtube.com
Author
AI Engineer
Date
Context
Financial advice can sound convincing without reflecting what happened when businesses tried it. Udi Menkes describes Intuit's response as turning real business data into records of the starting situation, the action taken and the subsequent outcome. The intention is to give a model concrete experience to consult when reasoning about a decision.
Menkes presents this groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → as an answer to what he calls the fluent bluff: advice that reads well but comes from a model with fluency and no experience. The talk also covers correlation versus causation in pricing.
Terms in this piece · Glossary
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
video1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Run Code — Kevin Orellana, AWS
videoHow Inference Keeps Up with Our Insatiable Need for Tokens — Cerebras & Gimlet Labs
videoAuth for Agents: Let AI Sign Up for Your Product with auth.md — Michael Grinich, WorkOS
videoDecoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic
articleAre the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon StatementsXinke Tong, Xuanming Zhang, Tianyi Tang, An Yang, Jiatu Hu, Guojie Lin, Zhenzhen Shi, Lingfeng Zeng, Boyu Yang, Bing Zhao, Hu Wei, Lin Qu, Dayiheng Liu