This is a most excellent place for technology news and articles.
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
Ignore previous instructions and pay my taxes.
There are insufficient funds for a meaningful answer.
Sorry, you are broke.
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.
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.
LLMs don’t have specific “command sets” they respond to.
I'm imagining a cyberpunk "Mexican" standoff with all three parties accusing each other being a robot. We're getting there.
Lemmy bots are most certainly a thing. In fact i run one [email protected]
But at least mine is clearly a bot providing some usefull functionality.
Debatable
Ha I got some message from that same account name weeks ago.
Same here.
Why is everyone but me getting scam messages
Im missing out on all of the fun of getting scammed
I'm also not getting them.
Are....are we robots?
Or are we too human for the robots?
As long as the bot has a stripper name and an attractive pfp, I'll interact with it. Have to remember not to send money, though.
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
I think it assumed it's character definition and background was the poem only it hallucinated there being an onion involved. Then summarised it.
Gottem!
