Hacker News 50 on Nostr: Kimi K1.5: Scaling Reinforcement Learning with LLMs Link: ...
Published at
2025-01-21 10:35:06Event JSON
{
"id": "394150e77ff1c731617fe1a49e07577cda2bd71fe4151e6d18d27ff682450164",
"pubkey": "c054332e25ef1ca0feebcd580622613bed81fec31e41f52f27a644c993cd67ae",
"created_at": 1737455706,
"kind": 1,
"tags": [
[
"proxy",
"https://social.lansky.name/users/hn50/statuses/113865897193885398",
"activitypub"
]
],
"content": "Kimi K1.5: Scaling Reinforcement Learning with LLMs\n\nLink: https://github.com/MoonshotAI/Kimi-k1.5\nDiscussion: https://news.ycombinator.com/item?id=42777857",
"sig": "4ef5477674ac51839bbd93af40fa623808490f6f05790bbb86e82f9c4fb626000e975e624ebe5df12f7891d1c1a34bf331c79848aa0b08b72d75a29c2df822d1"
}
