It's Comically Easy to Trick ChatGPT Into Saying Things About People That Are Completely Untrue
I think it's dangerous .” As Germain explains, the devious trick ... What if someone tricks an AI into spreading harmful lies about somebody else?
Read the original at futurism.com ↗
- Topics
- AI Safety & Existential Risk
- Mentions
- ChatGPTOpenAI
- Tracked via
- “dangerous AI”