Event JSON
{
"id": "b0a2104cfc45aa9f783959e3d7a9f9e7a98238cdd88803eea306e08edbb20de5",
"pubkey": "e0dd414aeab6feb747dc83623d2aa89d18b00c8d61b9199fd4d82ceba8a2d48b",
"created_at": 1737921699,
"kind": 1,
"tags": [
[
"e",
"6efe4453e83cb64862f16e4f8425d638358033ef384d1f2ac178dd1453c913d4",
"wss://relay.primal.net",
"root",
"76c71aae3a491f1d9eec47cba17e229cda4113a0bbb6e6ae1776d7643e29cafa"
],
[
"e",
"0eb8a8a8a6d0818c6c1cc2474f3c4e4dd1783eeaebefd339f44d57ea81bbb683",
"wss://relay.primal.net",
"reply"
],
[
"p",
"76c71aae3a491f1d9eec47cba17e229cda4113a0bbb6e6ae1776d7643e29cafa",
""
],
[
"p",
"e0dd414aeab6feb747dc83623d2aa89d18b00c8d61b9199fd4d82ceba8a2d48b",
""
],
[
"p",
"6c516eefe1dfc59598eb79162f909abead01062d7f2bb2e89b87fde05d928e2f"
],
[
"r",
"wss://auth.nostr1.com/",
"read"
],
[
"r",
"wss://nos.lol/"
],
[
"r",
"wss://nostr.mom/"
],
[
"r",
"wss://relay.0xchat.com/",
"read"
],
[
"r",
"wss://relay.damus.io/"
],
[
"r",
"wss://relay.primal.net/"
]
],
"content": "Most LLM benchmarks are typically designed with specific targets in mind, such as coding or language understanding. However, I believe the time is ripe for also having cross-model challenges. I was curious to see if anyone has already explored or implemented this approach.",
"sig": "69c8a14e63378529d1db2f9c22d8c193dc324cd4f3e86866d0bdcc930028401e0969bacbc143630e9eee95eb288a15cac4196802f17751d5046d9229c76f01f0"
}
