TechTakes

1394 readers

62 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 1 year ago

MODERATORS

[email protected]

a collection of thousands of prompts attempting to control the idiot genie of ChatGPT (github.com)

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

7 comments fedilink hide all child comments

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

[–] bitfucker 5 points 4 months ago (1 children)

So, you know LLM has a context window right? That means context overflow is a valid LLM attack strategy if you are somehow able to send more stuff than what is allowed.

[–] [email protected] 7 points 4 months ago (1 children)

and your point is?

[–] bitfucker 6 points 4 months ago* (last edited 4 months ago) (1 children)

Nothing? I'm pointing out another way to "attack" some LLM?

[–] [email protected] 9 points 4 months ago (2 children)

Probably would have been easier when the context window wasn't 128k.

Though what the point would be should someone actually achieve that eludes me a bit.

[–] bitfucker 10 points 4 months ago (1 children)

I don't know man. Maybe a chat bot for help center that forgot they shouldn't give refund or non existent promotion?

[–] [email protected] 1 points 4 months ago

I have LLMs translate novels, I can tell when they run over the window because they forget characters' gender half way through, things like that. Lots of legal documents are even longer, maybe.