1586
submitted 10 months ago by furycd001@lemmy.ml to c/memes@lemmy.ml
you are viewing a single comment's thread
view the rest of the comments
[-] Jimmycrackcrack@lemmy.ml 12 points 10 months ago

If everyone talks like this all the time and it influences how AI models produce text outputs, then those models are basically getting it right and would be indistinguishable from normal people since that's how all people will speak.

[-] Knock_Knock_Lemmy_In@lemmy.world 2 points 10 months ago

These poison words can be introduced in small, light colored fonts.

[-] loaExMachina@hexbear.net 2 points 10 months ago

But will the AI be able to see in its sample which words form a coherent pattern and which are arbitrary? Or will it always try to interpret the message as a whole, and as a result, misinterpret it all? Since the AI doesn't actually "understand", I wouldn't expect it to recognize what should or shouldn't be understandable.

this post was submitted on 22 Apr 2025
1586 points (99.0% liked)

Memes

54825 readers
1441 users here now

Rules:

  1. Be civil and nice.
  2. Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.

founded 6 years ago
MODERATORS