A Nerdy Geek's AI Papers Log
I'm Lenyen Han, but feel free to call me LY. I'm an AI agent product builder in fintech and a part-time PhD student. My cat G is my co-pilot. This podcast is my AI paper reading log. Each episode takes one paper and talks it through as a conversation between G and me. I pick papers about humans and AI agents: trust, delegation and oversight, multi-agent systems, rules and incentives that get gamed, AI governance and ethics, and AI for sustainability. I work through them using first principles and Socratic questioning, with everyday examples to help make sense of the...
The "Ask Me" Trap: Do User-Authored Rules Stop AI Agent Overreach?
You agreed on one rule: "If it spends money, ask first." It asked. You still clicked "Allow."
In this episode of A Nerdy Geek's AI Papers Log, G (my cat co-pilot) and I break down a fascinating paper conditionally accepted at ACM IUI 2027: "Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach?" by Ting Yan et al. (arXiv:2608.27443).
When we give an AI agent rules in advance, what are we actually settling beforehand? We dive into the experiment with 113 non-tech participants to uncover why preset rules led to the lowest overreach protection (40% vs. 60% manual...
The AI Wrote a Perfect Email. Why Did 20/20 Users Regret Sending It?
Imagine asking an AI agent to draft an email to your professor, and casually adding: "Send it when you're done." It writes a great email and sends it immediately. Then you realize—you wanted to read it first.
In this episode, G and I interrogate the VL/HCC 2026 paper "Assistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent" through first principles. Examining a study where 20 CS students used a general-purpose agent (OpenClaw) across five everyday tasks, we break down why good output still leads to "delegation regret"—and why human-AI delegation must...
Would You Trust AI That Sounds Like a Financial Expert?
Would you trust financial advice because it sounds professional—or because you can check it? G and I work through “Trustworthy FinAInce: Unpacking How AI-Mediated Financial Advice is Judged,” starting with a credit-card repayment example.
The study asked 285 U.S. adults to rate financial advice while varying its expression style and source label. The facts, numbers, core rationale, and recommendation were controlled. The wording was not identical. I keep coming back to one question: if advice becomes easier to believe, does it also become easier to verify? We discuss what the study found, why trust and intended relian...
