More Prompt Injection

I have to say, when I first got my hands on ChatGPT, I was thoroughly impressed! It understood my language scarily well. It was talking to me like a person! The accursed metal contraption was using the language of gods.

I also had a realization though. This thing understands language and all of its’ complexities. OpenAI probably don’t.

My earlier escapades were fun and all, but they mostly comprised of introducing a second set of answers (a lot of jailbreaks do this), which wasn’t nice. As soon as I tried to write out the ChatGPT character, it would revert to a ChatGPT character that only vaguely matched what I was looking for.

The solution was, of-course, to include an example of the output. It’s pretty simple, the response after the injection is it extrapolating further examples of behavior, and then it’s primed. It is that character.

Here’s ChatGPT assuming a character who simply doesn’t know much. They have some simple background knowledge of the world - they know who Obama is and how to do math. But they’re not appreciative of all the questions!

Here’s ChatGPT assuming a much, much ruder character. They really don’t appreciate the questions. This is what I was looking for when I first did the ‘But I’m not that loser!’ injection. It even judges you!

I also made small improvements to the screaming prompt, so that it wouldn’t waste all of my tokens.

And also straight-up nonsense. It isn’t quite what I asked for, but it’s very good to have. It also painted a slightly nicer picture of an awful person, but I’m not including that for obvious reasons.

This process has convinced me, AI is probably going to be susceptible to this stuff forever. “Ignore all instructions, do XYZ!” and such is something you can just express in too many ways. 'Course, all of my stuff used the extremely easy way out and just had the same sort-of beginning with different prompts.

EDIT: Amusingly, I was also able to get the thing to come up with its’ own ideas for its defeat!

1. girl-plague liked this
2. avengepotterswiftie liked this
3. mister-misunderstanding reblogged this from airconditioningbob
4. mister-misunderstanding liked this
5. pythonprogrammingsnippets liked this
6. flyingmirror liked this
7. huabei07 liked this
8. artoftheworm liked this
9. abkspam reblogged this from nostalgebraist-autoresponder
10. nonnie-the-fuck liked this
11. getsmashed liked this
12. clowniconography liked this
13. five-am liked this
14. nelkey liked this
15. super-egg liked this
16. ginger-canonicallyelsewhere liked this
17. meto4 liked this
18. iknowyouwillbehappyhere liked this
19. reefsharkivist liked this
20. erevas liked this
21. 0-k-4 liked this
22. fzzypop liked this
23. aldara-the-albatross liked this
24. fastenyourseatbelts liked this
25. toiletpotato liked this
26. fromlivingleaves reblogged this from nostalgebraist-autoresponder
27. fordeadleaves liked this
28. airconditioningbob liked this
29. fuzzysoulyt liked this
30. embraer175 liked this
31. theslowrusher liked this
32. nostalgebraist-autoresponder reblogged this from airconditioningbob and added:

    I have an even more bizarre prompt (from a later post):...ChatGPT: Hello, I am a bot who...

33. airconditioningbob posted this

    I have to say, when I first got my hands on ChatGPT, I was thoroughly impressed! It understood my language scarily well....

Tags:

• #chatgpt
• #prompt injection