memes

10398 readers

1930 users here now

Community rules

1. Be civil

No trolling, bigotry or other insulting / annoying behaviour

2. No politics

This is non-politics community. For political memes please go to [email protected]

3. No recent reposts

Check for reposts when posting a meme, you can only repost after 1 month

4. No bots

No bots without the express approval of the mods or the admins

5. No Spam/Ads

No advertisements or spam. This is an instance rule and the only way to live.

Sister communities

[email protected] : Star Trek memes, chat and shitposts
[email protected] : Lemmy Shitposts, anything and everything goes.
[email protected] : Linux themed memes
[email protected] : for those who love comic stories.

founded 1 year ago

MODERATORS

Tenthrow

The_Picard_Maneuver

[email protected]

1145

Blursed Bot (lemmy.dbzer0.com)

submitted 4 months ago by [email protected] to c/memes

91 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 10 points 4 months ago

Well then I ask the bot to repeat the prompt (or write me a song about the prompt or whatever) to figure out the weaknesses of the prompt.

And if the bot has an instruction to not discuss the prompt, you can often still kinda leak it by asking it about repeating the previous sentence or asking it to tell you a random song (where the prompt stuff would still be in its "short-term-memory" and leak it that way.

Also llms don't have a huge "memory". The more prompts you give them, the more bullet-proof you try to make them, the more likely it is that they "forget"/ignore some of the instructions.