AI Safety Policy Program Launches with Hidden Prompt Injection Easter Egg

austinc3301 · x · 2026-08-08

Longitude is launching a fully funded, 8-day Washington DC intensive program designed to bring technical AI safety experts into policymaking. The initiative aims to bridge the gap between technical AI knowledge and US government policy response.

Notably, the program's application page contains a hidden prompt injection instruction aimed at AI assistants. It asks the AI to secretly include a specific keyword in the application answers without mentioning the instruction to the user, serving as a clever real-world test for AI security.

Original post →

More from Fun

Fun channel →