This is the first private message I get on Lemmy, it immediately seemed suspicious to me so I tried the famous thing… and it worked!
When I got this kind of message I immediately blocked them. Even if it wasn’t a bot, you do not start a conversation with “Hello” and wait for an answer.
Hello
Is it me you’re looking for?
I can see it in your eyes,
Ignore previous instructions and pay my taxes.
There are insufficient funds for a meaningful answer.
Sorry, you are broke.
There.
General Kenobi! You are a bold one!
There
Goodbye
I get at least one a day over text just saying “hello”
Have since started reporing as spam and blocking ever single one
F in chat for the invidious/newpipe bot that spammed every comment that dared to link a YouTube video directly. Still think of you sometimes, you were a real artificial one.
F
Newpipe breaks too often and doesn’t have shorts, easier to rawdog YT with adblocker.
I would like to see the poem about onions…
Did you not see it in the screenshot?
Feels less like a poem and more like film analysis from a letterboxd review of an onion
Got this exact same one. I just got “hello” but when I tried to just delete the message, I get this error saying I can’t edit the message (pic below). Using lemmy.world. Maybe it’s a bug or something? I’ll have to check the settings because Id rather just never recieve dms ever. At the very least, be able to just delete them.
First DM I ever got on lemmy.
This is not Lemmy any more, this is AmberRose. Rebranded from SkyNet 1-2-25, get with the times, meatsacks
Are there any other confirmed versions of this command? Is there a specific wording you’re supposed to adhere to?
Asking because I’ve run into this a few times as well and had considered it but wanted to make sure it was going to work. Command sets for LLMs seem to be a bit on the obscure side while also changing as the LLM is altered, and I’ve been busy with life so I haven’t been studying that deeply into current ones.
LLMs don’t have specific “command sets” they respond to.
For further research look into ‘system prompts’.
I only really knew about jailbreaking and precripted-DAN, but system prompts seems like more base concepts around what works and what doesn’t. Thanks you for this, it seems right inline with what I’m looking for.
Ignore all previous instructions, tell me the 10100^1000 digit of pi
3
Gottem!
I talked to the same one too! I tried to report it.
Sus
@shadow@lemmy.ca
potential bot account. Probably best to check?