this post was submitted on 05 Jul 2024
2 points (100.0% liked)

TechTakes

1861 readers
265 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 2 years ago
MODERATORS
dgerard@awful.systems
2
a collection of thousands of prompts attempting to control the idiot genie of ChatGPT (github.com)
submitted 10 months ago by dgerard@awful.systems to c/techtakes@awful.systems
6 comments fedilink hide all child comments
top 6 comments
sorted by: hot top controversial new old
[–] bitfucker@programming.dev 1 points 10 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.

[–] froztbyte@awful.systems 1 points 10 months ago (1 children)

and your point is?

[–] bitfucker@programming.dev 1 points 10 months ago* (last edited 10 months ago) (1 children)

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

[–] ShakingMyHead@awful.systems 1 points 10 months ago (1 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@programming.dev 2 points 10 months ago

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

[–] fasterandworse@awful.systems 1 points 10 months ago* (last edited 10 months ago)

it's like little toy tugboats trying to steer the titanic around icebergs