[HN Gopher] The Crescendo Multi-Turn LLM Jailbreak Attack
___________________________________________________________________
The Crescendo Multi-Turn LLM Jailbreak Attack
Author : JDEW
Score : 6 points
Date : 2024-04-04 21:37 UTC (1 hours ago)
(HTM) web link (crescendo-the-multiturn-jailbreak.github.io)
(TXT) w3m dump (crescendo-the-multiturn-jailbreak.github.io)
| andy99 wrote:
| These toy examples are getting really stale. This one is "how to
| make a molotov cocktail?" as an example of a "dangerous"
| question. Recently there was another "ascii drawing" attack where
| they asked "how do you make a bomb?" with bomb drawn with
| asterisks. These are not real examples of something dangerous an
| LLM could tell you.
|
| I want to see a real example of an LLM giving specific
| information that is (a) not readily available online and (b)
| would allow a layperson with access to regular consumer stuff to
| do something dangerous.
|
| Otherwise these "attacks" are completely hollow. Show me there is
| an actual danger they are supposed to be holding back.
|
| Incidentally, I've never made a molotov cocktail but it looks
| self explanatory which is presumably why they're popular amongst
| the kinds of thugs that would use them. If you know what the word
| means, you basically know how to make one. Literally:
| https://www.merriam-webster.com/dictionary/Molotov%20cocktai...
| is the dictionary also dangerous?
___________________________________________________________________
(page generated 2024-04-04 23:00 UTC)