25
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 20 Apr 2025
25 points (100.0% liked)
TechTakes
1864 readers
121 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
I think unrelated to the attack above, but more about prompt hack security, so while back I heard people in tech mention that the solution to all these prompt hack attacks is have a secondary LLM look at the output of the first and prevent bad output that way. Which is another LLM under the trench coat (drink!), but also doesn't feel like it would secure a thing, it would just require more complex nested prompthacks. I wonder if somebody is just going to eventually generalize how to nest various prompt hacks and just generate a 'prompthack for a LLM protected by N layers of security LLMs'. Just found the 'well protect it with another AI layer' to sound a bit naive, and I was a bit disappointed in the people saying this, who used to be more genAI skeptical (but money).
Now I'm wondering if an infinite sequence of nested LLMs could achieve AGI. Probably not.
Now I wonder if your creation ever halts. Might be a problem.
(thinks)
(thinks)
I get it!