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

7 comments fedilink hide all child comments

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

[-] froztbyte@awful.systems 7 points 10 months ago

and your point is?

[-] bitfucker@programming.dev 6 points 10 months ago* (last edited 10 months ago)

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

[-] ShakingMyHead@awful.systems 9 points 10 months ago

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.

[-] nfultz@awful.systems 1 points 10 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.

load more comments (2 replies)

this post was submitted on 05 Jul 2024

44 points (100.0% liked)

TechTakes

1848 readers

74 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