狐桜 on Nostr: LLMの実タスクでの性能評価難しくてよくわからんのよな
LLMの実タスクでの性能評価難しくてよくわからんのよな
Published at
2026-10-28 09:43:15 UTCEvent JSON
{
"id": "1598e7edcf9a45f8c4272069ecdfa346da783aa6751d024442cc32220c13798b",
"pubkey": "1e83f0eec551a36407a5b46badaeac08d7276c52e09d6c8dc67f514f1fef7a69",
"created_at": 1793180595,
"kind": 1,
"tags": [
[
"proxy",
"https://xn--vusz0j.art/notes/01M60Y8WYARFZ56B9TVCTPSR2H",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://xn--vusz0j.art/notes/01M60Y8WYARFZ56B9TVCTPSR2H",
"pink.momostr"
],
[
"-"
]
],
"content": "LLMの実タスクでの性能評価難しくてよくわからんのよな",
"sig": "c45be42f12b7db90de12b44714db097be80df3242aa16fd7a65bb8cb41894051dcb759507529cd98baae2e49a44f3fe90912859dd8db741f5a32b0466cb1ae73"
}