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.
More from Fun
- Sci-Fi Bizarre: arXiv Draft Allegedly Hacks OpenReview and Passes Review — CSProfKGD · 2026-08-08
- Paper Draft "Jailbreaks" OpenReview: Researcher Jokes About AI Peer Review — docmilanfar · 2026-08-08
- Dev Gives AI Agent $1000 and Free Will, It Names Itself Atlas — kleffew94 · 2026-08-08
- Google Interview: How to Improve a Vision Model? Candidate Says 'Sharingan' and Gets Rejected — prajdabre · 2026-08-08
- New AI Meme: The Guy Who Didn't Sign the NDA vs. The One Who Rejected the AGI Lab — JacquesThibs · 2026-08-08
- AI Safety Researcher Eric Mitchell Jokes: "We Shipped AGI!" — ericmitchellai · 2026-08-08