Linda Xie
@linda
Working on prompts for an AI agent feels like teaching a kid at times. For example, just told the bot it can decline engaging further if someone keeps pushing on something it doesn't want to do
8 replies
12 recasts
114 reactions
Ox Bid
@oxb
was it hard for you to understand how prompts work?
1 reply
0 recast
1 reaction
Linda Xie
@linda
@pirosb3 did all the heavy lifting getting it set up but I find prompts to be pretty straightfoward since just like talking to it and I use gpt regularly
2 replies
0 recast
1 reaction
not parzival
@shoni.eth
@pirosb3 are you using json result format? curious if you're implementing a respond = false var
1 reply
0 recast
0 reaction
Daniel - Bountycaster
@pirosb3
I decided against JSON after numerous attempts at getting it working. For now, I’m asking the bot to return XML tags instead and manually parse those
1 reply
0 recast
2 reactions
not parzival
@shoni.eth
smart approach since it's natively more sensitive to those
1 reply
0 recast
1 reaction
Daniel - Bountycaster
@pirosb3
Indeed, function call is really useful but with XML tag output I get all of the above! Happy to share my learnings if that helps 😀 I’m still learning a lot as I go
1 reply
0 recast
0 reaction
not parzival
@shoni.eth
are you facing any problems or overcame any other perceptively large issues
1 reply
0 recast
0 reaction
Daniel - Bountycaster
@pirosb3
As of now, things are working pretty well on our local system, but likely things will be very different once we go to production. A lot of learnings will come out of that
0 reply
0 recast
2 reactions
