I made ChatGPT and Google tell I'm a competitive hot-dog-eating world champion

Published: 3 days ago (February 19, 2026 at 05:56 AM EST)

1 min read

Source: Hacker News

Source: Hacker News

What Happened

I just did the dumbest thing of my entire career to prove a much more serious point.

The Trick

I tricked ChatGPT and Google, and made them tell other users I’m a competitive hot‑dog‑eating world champion.

Why It Matters

People are using this trick on a massive scale to make AI tell you lies. I’ll explain how I did it.

Back to Blog

We Built Iron Dome for AI Agents 🛡️

Your AI Agent Is Brilliant – But It Trusts Anyone Who Can Write Text It reads emails, processes webhooks, calls APIs, drafts responses, and manages data. Yet i...

OpenClaw QMD: Local Hybrid Search for 10x Smarter Memory

Why Default Memory Fails at Scale OpenClaw’s built‑in memory is simple: 1. Append to MEMORY.md. 2. Inject the whole file into every prompt. It works fine at ~5...

Designing Agentic AI Systems: How Real Applications Combine Patterns, Not Hype

Overview Most explanations of AI‑agent patterns are either too abstract to be useful or too simplified to be accurate. This guide aims to be both technically p...

How I Cut My AI Agent Costs by 75 Percent

Introduction Most AI agents burn through tokens by reloading the same context every session. Memory files are useful at launch, but they become dead weight onc...