What does this achieve?
I think it's inevitable that group chats will involve LLM agents in the future.
Questions about LLMs in Group Chats
11–20 of 21 posts
Re: Questions about LLMs in Group Chats
#12Re: Questions about LLMs in Group Chats
#13Re: Questions about LLMs in Group Chats
#14Re: Questions about LLMs in Group Chats
#15Earlier quoted context omitted.
For all the same reasons you talk to humans...
To find out what’s going on in their lives and to arrange to meet up socially?
Is that the only thing you talk to your friends about?
I mean yeah literally you could talk about your plans [i.e. by yourself or with the other real people] or what's going on in your life and have the bot chime in with thoughts too. You could talk about food, philosophy, politics, travel, complain about stuff, get advice for relationships or work, gossip. All in a group chat setting.
It's not hard to imagine a bot that's able to contribute here and there in a meaningful way in any of these subjects, and other unlimited subjects. But perhaps you weren't open to it in the first place so I'm not going to try to convince you further if you don't buy it; If you don't want to really give it consideration then nobody is going to convince you otherwise.
Re: Questions about LLMs in Group Chats
#16Earlier quoted context omitted.
I think it's inevitable that group chats will involve LLM agents in the future.
For?
Ideally? Automatically answering support questions in open source discord channels, automatically taking minutes in business slack conversations.
Cynically? Your group chat is hosted by a tech company. That tech company wants to tell investors they've got an LLM, and show user counts going up. And the fastest way to boost user counts on a failing product is to make it an always-on feature of a successful product.
Re: Questions about LLMs in Group Chats
#17I did a small test a year and a half ago (very basic) and it was already funny xD
Re: Questions about LLMs in Group Chats
#18What does this achieve?
Main thought is just that there are tons of situations that involve more than 2 people being in a discussion. some the of links I mentioned in the post get into this with the "facilitator" model.
Moderation/mediation is probably the most obvious thing "usecase." I'm more interested in just pushing the limits of what the language models can do and see what kind of things they'll do.
There's a corner of the internet interested in these models as a form of "alien intelligence." Don't immediately know what the application would be, but the results are super interesting
Re: Questions about LLMs in Group Chats
#19I'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?
Curious what kind of things you had the model look for? Did they have any kind of goal or was it more a "vibe" thing.
Also would it only respond if a message was directed at it or could they proactively decide to join a conversation?
Re: Questions about LLMs in Group Chats
#20Earlier quoted context omitted.
For?
Ideally? Automatically answering support questions in open source discord channels, automatically taking minutes in business slack conversations. Cynically? Your group chat is hosted by a tech company. That tech company wants to tell investors they've got an LLM, and show user counts going up. And the fastest way to boost user counts on a failing product is to make it an always-on feature of a successful product.
I don't think your first usecases are applicable to what people normally call "group chats"