
Darryl Yeo đ ïž
@darrylyeo
3617 Following
10463 Followers
4 replies
4 recasts
34 reactions
0 reply
0 recast
0 reaction
8 replies
3 recasts
54 reactions
54 replies
66 recasts
370 reactions
13 replies
1 recast
14 reactions
0 reply
1 recast
6 reactions
2 replies
2 recasts
12 reactions
146 replies
132 recasts
880 reactions
0 reply
0 recast
0 reaction
1 reply
0 recast
1 reaction
0 reply
0 recast
0 reaction
9 replies
34 recasts
50 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
5 reactions
0 reply
0 recast
1 reaction
34 replies
37 recasts
370 reactions

What does an AI-first social network look like? Some thoughts.
First, you can prototype it with Farcaster. You donât need to reinvent users, wallets, the feed, any of that. So that alone speeds you up.
Second, open source models are now cheap enough to run that you can just put them behind a normal button. Xâs Grok integration is a good example.
Third, there is tremendous room for an AI which is prompted not just on immediate context (your post) but on social context (your past posts and those of your friends). It could autogenerate prompts it thinks youâd like.
Fourth, AI improvements on seemingly simple things like image upload widgets could be profound. You could automatically search for similar images, upscale them, auto-annotate them, or do something else.
Fifth, AI could enforce a certain style in a community. As heavy-handed example, every post could be rewritten in Olde English. If you opted into this kind of moderation, it could produce unique communities. Like filters, but for text. 24 replies
20 recasts
148 reactions
1 reply
1 recast
1 reaction
0 reply
0 recast
1 reaction
1 reply
0 recast
1 reaction