this post was submitted on 12 Apr 2024
506 points (100.0% liked)

196

16503 readers
2494 users here now

Be sure to follow the rule before you head out.

Rule: You must post before you leave.

^other^ ^rules^

founded 1 year ago
MODERATORS
moss@lemmy.blahaj.zone
greembow@lemmy.blahaj.zone
moss@lemmy.world
queue@beehaw.org
funky_rodent@lemmy.blahaj.zone
PeachyMcPeachface@lemmy.blahaj.zone
threegnomes@lemmy.blahaj.zone
greembow@lemmy.world
remotelove@lemmy.ca
Roflmasterbigpimp@feddit.de
qaz@lemmy.world
A_Very_Big_Fan@lemm.ee
qaz@lemmy.blahaj.zone
qaz@lemmy.ca
A_Very_Big_Fan@lemmy.world
qaz@lemmy.dbzer0.com
Qaz@lemmy.ml
qaz@sh.itjust.works
qaz@lemmy.sdf.org
506
Beep boop, I don't want this rule (lemmy.world)
submitted 7 months ago by ZILtoid1991@lemmy.world to c/196@lemmy.blahaj.zone
51 comments fedilink hide all child comments
 
you are viewing a single comment's thread
view the rest of the comments
[–] Buddahriffic@lemmy.world 8 points 7 months ago

I think the applicant including "don't reply as if you are an LLM" in their prompt might be enough to defeat this.

Though now I'm wondering if LLMs can pick up and include hidden messages in their input and output to make it more subtle.

Just tested it with gpt 3.5 and it wasn't able to detect a message using the first word after a bunch of extra newlines. When asked a specifically if it could see a hidden message, it said how the message was hidden but then just quoted the first line of the not hidden text.