someone on Nostr: QwQ 32B was published today and I already tested it for AHA Leaderboard. The results ...
QwQ 32B was published today and I already tested it for AHA Leaderboard. The results are not that good! It did better than its predecessor (Qwen 2.5) in fasting and nutrition but worse in domains like nostr, bitcoin and faith. Overall worse than previous.
LLMs are getting detached from humans. Y'all have been warned, lol.
Published at
2025-03-06 05:08:16Event JSON
{
"id": "6e17506b2464ad8615045afe7684e3a509beee4c2aa21cb5f9c2af58b4cbad2d",
"pubkey": "9fec72d579baaa772af9e71e638b529215721ace6e0f8320725ecbf9f77f85b1",
"created_at": 1741237696,
"kind": 1,
"tags": [
[
"client",
"Yakihonne",
"31990:20986fb83e775d96d188ca5c9df10ce6d613e0eb7e5768a0f0b12b37cdac21b3:1700732875747"
]
],
"content": "QwQ 32B was published today and I already tested it for AHA Leaderboard. The results are not that good! It did better than its predecessor (Qwen 2.5) in fasting and nutrition but worse in domains like nostr, bitcoin and faith. Overall worse than previous.\n\n https://image.nostr.build/965699957d9bab7158ca4a5c6b5f70e8a9832d63fb803f34de3fe5b0e341b3a7.png\n\nLLMs are getting detached from humans. Y'all have been warned, lol.\n\n",
"sig": "2c7d64b1c07aac743bceab693036d099d946dcebc4f1f94166d8d9ec391670646e2176c46b1a11b3e4d8572f10abf54f3d60192f85452753f3fbfd2d6c1b709c"
}
