17
you are viewing a single comment's thread
view the rest of the comments
[-] ovid@fosstodon.org -5 points 2 months ago

@FRACTRANS @gerikson

Nice job! This is a fairly common trick with AI. In traditional programming, there's a clear separation between code and data. That's not the case for GenAI, so these kinds of hacks have worked all over the place.

[-] self@awful.systems 8 points 2 months ago

lisp programmers in shambles as I prompt inject another s-expression

[-] bitofhope@awful.systems 8 points 2 months ago

I don't want to have to make legal threats to an LLM in all data not intended for LLM consumption, especially since the LLM might just end up ignoring it anyway, since there is no defined behavior with them.

this post was submitted on 26 Aug 2024
17 points (100.0% liked)

TechTakes

1427 readers
111 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