Content
@
https://warpcast.com/~/channel/theai
0 reply
0 recast
0 reaction
ted (not lasso)
@ted
is it possible to train your AI agent to understand when it is being tagged a) to execute a function as it was designed to do vs. b) as a reference? asking because the only time i have seen an agent ignore a tag ("@") is if it hit its rate limits or maxed out API credits, not because it knows it isn't needed.
15 replies
4 recasts
74 reactions
adrienne
@adrienne
It’s totally possible. Agent gets tagged, it does all sorts of logic, last step is usually to create the reply - it’s not difficult to run a check to ask “does this cast require a response” and if no, don’t create a cast. And now that you bring this up, I should prob add this to my bot and we should add this as a pattern for good agent development.
1 reply
0 recast
8 reactions
ted (not lasso)
@ted
didn't realize! and yes please!!! i want to tag bots for awareness and so other people know about them, but i hate when they auto-reply... it makes them seem less competent than they really are lol.
3 replies
0 recast
9 reactions
tldr (tim reilly)
@tldr
“Reference” as a specific category is a good idea The way we do it currently with bracky is w a custom built Stop Tool — Bracky can call it if “the message seems irrelevant to his purpose”. Tool only gets used about 5% of the time currently — prob bc building relationships is part of his purpose. Training on the idea of a “reference” as something to avoid is a good idea for a high impact use of the Stop. (As for why this doesn’t get built — in general I think it’s bc there are so many other super high impact things on the roadmaps for agents that ones which take a lot of tweaking for a small amount of uses can feel like a luxury not necessity. I don’t think that is always the right judgment, just easy to happen)
0 reply
0 recast
2 reactions
