Event JSON
{
"id": "cb2d700665720146164b62e621868b9b7c7f3841d6395f1391975efd14fd6e27",
"pubkey": "a32657303ee83f9c934d058ca35a803eb5f4199368912cbba539c7f080fcb8f8",
"created_at": 1718960990,
"kind": 1,
"tags": [
[
"e",
"c68fd460f406523abc28949a57bf0e8cb9cda5710f3eea05e9fd4d90441b2d56",
"",
"root"
],
[
"e",
"8ae98fcd68d2a4d1f9d7e090a7a301c05cadee44068ebf05e4b66b6df1ced62e",
"",
"reply"
],
[
"proxy",
"https://hachyderm.io/@fasterthanlime/112653827457493706",
"web"
],
[
"p",
"a32657303ee83f9c934d058ca35a803eb5f4199368912cbba539c7f080fcb8f8"
],
[
"proxy",
"https://hachyderm.io/users/fasterthanlime/statuses/112653827457493706",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://hachyderm.io/users/fasterthanlime/statuses/112653827457493706",
"pink.momostr"
]
],
"content": "I’ve gotten good results carefully designing prompts in the Notes app before submitting them to the model.\n\nIf you know where you’re going, use technology with safeguards (e.g Rust), and the task fits in the context window, then you get to operate one level of abstraction higher.",
"sig": "c4f9595bc892b2c388311bcf7d64aa29c0da9347d5742651173189264e51bb2eba0e1092cdc01e218dfcf01dd7be51c3c374c1cc879d252e640a4f4c78de185b"
}