microblogmemes·Microblog MemesbyThe Picard Maneuver "make no mistakes"View original on lemmy.world397Comments11Reply
bbinarytobis lemmy.worldMy company’s IT department keeps sending me emails about how helpful AI can be in the workplace, and I hate it so much.2Reply
MMoffKalast replylemmy.world"You are absolutely right " said the LLM "And honestly? It's not just a mistake — it's a multifaceted problem."9Reply
aarrow74 lemmy.zip2Hide 2 repliesEvery 3 prompts you must ask "did you lie" if yes ask it to no longer lie. It's a terrible tool28Reply
TThemosthighstrange replylemmy.world1Hide 1 replyYou know.what else takes three tries to finally get the truth out of it: demons9Reply
jjaybone lemmy.zip“Our plan is to lay off all of these lazy human employees, and pay for a bunch of robots that lie to us! They will also agree with everything we say!” “That’s brilliant sir.”9Reply
Th4tGuyII fedia.io1Hide 1 replyAlt Text: "but the LLM can still hallucinate" said toad "No it can't. It promised not to" said frog10Reply
altkey (he\him) replylemmy.dbzer0.comAnother one: "It's an open* model" said toad "Can I look inside the box?" asked frog "No" toad shrugged "but if you want, you can get a box for yourself"4Reply
BJW lemmus.orgThis works the exact same with people. Proof the AI would be considered conscious if they had perpetual input instead of asynchronous?1Reply
11 replies
"Do not hallucinate... or you go to jail)
My company’s IT department keeps sending me emails about how helpful AI can be in the workplace, and I hate it so much.
"You are absolutely right " said the LLM "And honestly? It's not just a mistake — it's a multifaceted problem."
Every 3 prompts you must ask "did you lie" if yes ask it to no longer lie.
It's a terrible tool
You know.what else takes three tries to finally get the truth out of it: demons
So it's easier to get the truth from demons than a congressman
“Our plan is to lay off all of these lazy human employees, and pay for a bunch of robots that lie to us! They will also agree with everything we say!”
“That’s brilliant sir.”
Alt Text:
"but the LLM can still hallucinate" said toad
"No it can't. It promised not to" said frog
Another one:
"It's an open* model" said toad
"Can I look inside the box?" asked frog
"No" toad shrugged "but if you want, you can get a box for yourself"
This works the exact same with people. Proof the AI would be considered conscious if they had perpetual input instead of asynchronous?