Questions about LLMs in Group Chats
vineeth.io
Questions about LLMs in Group Chats
1–10 of 21 posts
Re: Questions about LLMs in Group Chats
#2[flagged]
Re: Questions about LLMs in Group Chats
#3What does this achieve?
Re: Questions about LLMs in Group Chats
#4I'm interested. Could you use a LLM function call to decide whether or not to respond instead of randomness so it feels more intelligent?
Also, I have no idea what the use case for this would be but making it work sounds cool and kinda fruitful.
Re: Questions about LLMs in Group Chats
#5I'm interested. Could you use a LLM function call to decide whether or not to respond instead of randomness so it feels more intelligent? Also, I have no idea what the use case for this would be but making it work sounds cool and kinda fruitful.
> Could you use a LLM function call to decide whether or not to respond
I've implemented this for a toy project before and it worked surprisingly well, yes! It can take some creative prompting to have the model understand which messages are actually directed at it, though, which I guess makes sense since every User message is _supposed_ to be?
Re: Questions about LLMs in Group Chats
#6What does this achieve?
Fun and satisfaction of curiosity for me.
Re: Questions about LLMs in Group Chats
#7I'm interested. Could you use a LLM function call to decide whether or not to respond instead of randomness so it feels more intelligent? Also, I have no idea what the use case for this would be but making it work sounds cool and kinda fruitful.
> Could you use a LLM function call to decide whether or not to respond I've implemented this for a toy project before and it worked surprisingly well, yes! It can take some creative prompting to have the model understand which messages are actually directed at it, though, which I guess makes sense since every User message is _supposed_ to be?
What model did you use for this?
Re: Questions about LLMs in Group Chats
#8This is very interesting and thought provoking. On its face it sounds so simple - just put the bots in a room together and let them go at it. But of course it's much more complicated than that, at least if you want good and/or interesting results.
Re: Questions about LLMs in Group Chats
#9I'm interested. Could you use a LLM function call to decide whether or not to respond instead of randomness so it feels more intelligent? Also, I have no idea what the use case for this would be but making it work sounds cool and kinda fruitful.
> Could you use a LLM function call to decide whether or not to respond instead of randomness so it feels more intelligent?
Yes, and once you collect enough samples from the LLM you could train a SLM to do it faster and cheaper.
Re: Questions about LLMs in Group Chats
#10I've been contemplating these exact same thoughts and ideas, and indeed have been very surprised how little exploration there seems to be around these nuances!