jb55 on Nostr: If deepseek did reinforcement learning over chain of thought reasoning to train r1… ...
If deepseek did reinforcement learning over chain of thought reasoning to train r1… and alphago used reinforcement learning to find superhuman strategies in Go… maybe scaling up reinforcement learning on chain of thought reasoning will get us closer to superhuman reasoning and dare i say agi? Feels like we’re at the beginning of something huge.
Published at
2025-02-11 05:19:03Event JSON
{
"id": "4eb53815a86c848e5c1d9b0a44f2a809eaf9227f58f8abfb8778a1b5cee821e8",
"pubkey": "32e1827635450ebb3c5a7d12c1f8e7b2b514439ac10a67eef3d9fd9c5c68e245",
"created_at": 1739251143,
"kind": 1,
"tags": [],
"content": "If deepseek did reinforcement learning over chain of thought reasoning to train r1… and alphago used reinforcement learning to find superhuman strategies in Go… maybe scaling up reinforcement learning on chain of thought reasoning will get us closer to superhuman reasoning and dare i say agi? Feels like we’re at the beginning of something huge.",
"sig": "1548848bdd216a87da11ede48adf9afa8a0df0c4fff651e6de18c6bc45bb546c220a9af671f6bc92d0a5b564e78f854e1df644942536f18e44a28fd6e9d9631e"
}
