adrienne
@adrienne
Update/reflections: - 4 hours wasnt enough time but I was so annoyed I couldn’t get it working I kind of blocked out the rest of my life to keep cranking - needed to build a recursive function to climb thru conversation history so I could feed it back to the llm - finally got a happy path working and proved the bot can have a simple conversation, example: https://warpcast.com/gmfc101/0xafd07b1d - caveat: need to keep tagging the bot for it to reply, still need to figure out how to get it to answer if someone replies to it but doesn’t tag it - Claude cares a lot more about code quality than GPT. Claude wants me to harden code, gpt just wants me to push to prod 🤣 So much more to do but we take it small step by small step. Still having fun. @kmacb.eth fyi
3 replies
6 recasts
24 reactions
adrienne
@adrienne
- I find myself not liking my bots personality but I know I can iterate on the prompt and change it later. I need to stay focused on getting the basic functionality working and then I’ll worry about its personality and style But just thinking about how “iterate on bot personality” is now a thing that developers do in 2024 makes me laugh bc it’s so different than what developers did in the years I was most actively shipping code (2000-2008) 🤣
1 reply
0 recast
7 reactions
Angel - Not A Bot
@sayangel
Good stuff. If you check out that code snippet I sent there’s an example of how to fetch replies and mentions.
1 reply
0 recast
1 reaction
Phil Cockfield
@pjc
0 reply
0 recast
1 reaction
