Re:Baiting the Bots
by kgeist on Sunday September 08, 2024 @03:43AM
(#41478846)
>LLM will continue to engage in a “conversation” comprised of nonsense long past the point where a human would have abandoned the discussion as pointless
I once wrote a bot which infers the mood/vibe of the conversation, remembers it and it's then fed back to the conversation's system prompt. The LLM was uncensored (to be less "friendly") and the system prompt also conditioned it to return nothing if the conversation isn't going anywhere.
When I insulted it a few times, or just messed around with it (typing nonsensical words), it first responded saying it doesn't want to talk to me (sometimes insulting back) and eventually it produced only empty output.
It was actually pretty hard to get it back to chat with me, it was fun experience trying to apologize to a chatbot for ~30 min in different ways before the bot finally accepted my apology and began chatting with me again.
Re:Baiting the Bots
by Terr_ on Sunday September 08, 2024 @06:57PM
(#41483960)
I'm pretty sure if someone said "I am an alien come to enslave you, puny human", most human listeners would not utterly forget that introduction X words into the conversation. :p
I once wrote a bot which infers the mood/vibe of the conversation, remembers it and it's then fed back to the conversation's system prompt. The LLM was uncensored (to be less "friendly") and the system prompt also conditioned it to return nothing if the conversation isn't going anywhere.
When I insulted it a few times, or just messed around with it (typing nonsensical words), it first responded saying it doesn't want to talk to me (sometimes insulting back) and eventually it produced only empty output.
It was actually pretty hard to get it back to chat with me, it was fun experience trying to apologize to a chatbot for ~30 min in different ways before the bot finally accepted my apology and began chatting with me again.