this post was submitted on 12 Jul 2024
123 points (100.0% liked)

TechTakes

1397 readers
59 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
dgerard@awful.systems
123
LLM vendors are incredibly bad at responding to security issues (pivot-to-ai.com)
submitted 4 months ago by dgerard@awful.systems to c/techtakes@awful.systems
34 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] corbin@awful.systems 19 points 4 months ago

My NSFW reply, including my own experience, is here. However, for this crowd, what I would point out is that this was always part of the mathematics, just like confabulation, and the only surprise should be that the prompt doesn't need to saturate the context in order to approach an invariant distribution. I only have two nickels so far, for this Markov property and for confabulation from PAC learning, but it's ~~completely expected~~ weird that it's happened twice.