+1 on this. It’s worth noting that for ChatGPT, OpenAI actually had (has?) a bounty program for adversarial prompts; I spent a weirdly fun afternoon getting the AI to endorse Hitler, etc., and “won,” just to find out that my prize was… a water bottle lol.
+1 on this. It’s worth noting that for ChatGPT, OpenAI actually had (has?) a bounty program for adversarial prompts; I spent a weirdly fun afternoon getting the AI to endorse Hitler, etc., and “won,” just to find out that my prize was… a water bottle lol.