npub1f6a33pfyp67y8llhunlhrf855xm47n3fdqymvxfj7yx78c6vqf4scxpnql (npub1f6a…pnql)
"and it was clearly wrong" - Here's my theory: LLM's are useful if results are easy to verify.
In your example eyeballing can easily tell if the resulting shape is _similar_ to the input area. As I understand your use-case doesn't require too much precision, which is totally fine, but it's important to ask how much harder your problem would get if you wanted to make sure the input and output shapes are precise matches? Would you use an LLM to write some verification code? How do you decide if that code is correct? (I think in this particular case actual verification could be actually pretty easy, but I wanted to stick with the example)
buherator /
npub1n3…djee0
2024-03-23 09:55:29
in reply to nevent1q…l32m
Author Public Key
npub1n3p6whdpmt9k8rxzcmvrs053utg662lfrgdxh7dl9t04ff8sdk7qqdjee0Published at
2024-03-23 09:55:29Event JSON
{
"id": "4634961f01eea27d674f23feec4666a4aad101cbf09eedd239ca864851410029",
"pubkey": "9c43a75da1dacb638cc2c6d8383e91e2d1ad2be91a1a6bf9bf2adf54a4f06dbc",
"created_at": 1711184129,
"kind": 1,
"tags": [
[
"p",
"4ebb1885240ebc43fff7e4ff71a4f4a1b75f4e296809b61932f10de3e34c026b",
"wss://relay.mostr.pub"
],
[
"p",
"8b0be93ed69c30e9a68159fd384fd8308ce4bbf16c39e840e0803dcb6c08720e",
"wss://relay.mostr.pub"
],
[
"e",
"79403aa43b2e621848ffff5fb2b0429f339fceb963d1661d5e7f58bbc606c1da",
"wss://relay.mostr.pub",
"reply"
],
[
"proxy",
"https://infosec.place/objects/443d6681-8af4-4a88-a811-a7e565cf5bb4",
"activitypub"
]
],
"content": "nostr:npub1f6a33pfyp67y8llhunlhrf855xm47n3fdqymvxfj7yx78c6vqf4scxpnql \n\n\"and it was clearly wrong\" - Here's my theory: LLM's are useful if results are easy to verify. \n\nIn your example eyeballing can easily tell if the resulting shape is _similar_ to the input area. As I understand your use-case doesn't require too much precision, which is totally fine, but it's important to ask how much harder your problem would get if you wanted to make sure the input and output shapes are precise matches? Would you use an LLM to write some verification code? How do you decide if that code is correct? (I think in this particular case actual verification could be actually pretty easy, but I wanted to stick with the example)",
"sig": "6e21e42eed74c660f132425357818627acd2312dd7d63a740ad440750f6f023612e64858ffcd74f1f07cfe8f758ee9ce02c15cc9e6a9aad90e59a9bdf306fc4b"
}