Turns out that LLM summaries are actually useful.
Not for *summarizing* text -- they're horrible for that. They're weighted statistical models and by their very nature they'll drop the least common or most unusual bits of things. Y'know, the parts of a message that are actually important.
No, where they're great is as a writing check. If an LLM summary of your work is accurate then indicates what you wrote doesn't really have much interesting information in it and maybe you should try harder.
Dan Sugalski
npub182…lzysf
2024-10-23 13:11:23 UTC
Author Public Key
npub1820k96h86306z49k2f92eal40myuu28az5j6tmyy73wwpk5kukws4lzysfSeen on
wss://relay.momostr.pinkPublished at
2024-10-23 13:11:23 UTCEvent JSON
{
"id": "0eee94cc8183ce5ada5c0c89f66784fa566b88c4bd2366ed64d9aaaf34e77a7e",
"pubkey": "3a9f62eae7d45fa154b6524aacf7f57ec9ce28fd1525a5ec84f45ce0da96e59d",
"created_at": 1729689083,
"kind": 1,
"tags": [
[
"proxy",
"https://weatherishappening.network/@wordshaper/113356903751134576",
"web"
],
[
"proxy",
"https://weatherishappening.network/users/wordshaper/statuses/113356903751134576",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://weatherishappening.network/users/wordshaper/statuses/113356903751134576",
"pink.momostr"
],
[
"-"
]
],
"content": "Turns out that LLM summaries are actually useful.\n\nNot for *summarizing* text -- they're horrible for that. They're weighted statistical models and by their very nature they'll drop the least common or most unusual bits of things. Y'know, the parts of a message that are actually important.\n\nNo, where they're great is as a writing check. If an LLM summary of your work is accurate then indicates what you wrote doesn't really have much interesting information in it and maybe you should try harder.",
"sig": "ee4e04d9e61271dba418d8caa4bab59138cafa320d94a4f8c631572b93f353c427936f11a09115a2980281aafa4a68b3414a2f354aace76c9dbab4801f21d428"
}