Why Prompt Hacking is Important for AI Safety
Join AI Productivity Hub & Setup Your AI Second Brain in 10min: https://dub.sh/join-aiph ⬇️Resources mentioned in this video⬇️ 🚩HackAPrompt Competition: https://bit.ly/3VrKTAR 🚩Listen to the full Interview with Sander Schulhoff: https://spoti.fi/42oLiWK 🚩learnprompting.org http://bit.ly/3YvFids Say Hi on LinkedIn: https://www.linkedin.com/in/godajuskevi/ Timestamps: 00:00 Bing Chat Trying to Steal Money 01:26 Prompt Hacking Competition: HackAPrompt 02:08 Who is Behind This Competition 04:02 Why do OpenAI and Stability AI support this? 05:08 I reveal a Prompt Injection Attack on this website 06:18 Researchers are Hacking into LLM models Other resources: 🚩Prompt Injection video shown: https://greshake.github.io/ 🚩Research Paper Mentioned: https://arxiv.org/pdf/2302.12173.pdf🚩The Hacking of ChatGPT Is Just Getting Started : https://www.wired.com/story/chatgpt-jailbreak-generative-ai-hacking/ 🚩GPT-4 JAILBREAK AND HACKING VIA RABBITHOLE ATTACK: https://bit.ly/414xRdM For editing videos, I use Descript (here is my affiliate link if you don't mind and would like to support my channel): https://www.descript.com/?lmref=U_q-Kw Thank you so much for watching and joining me on this journey! Let me know in the comments what you would like to see more of in the future. Bye!
