jb55 on Nostr: idea: adversarial reinforcement learning of LLMs via gaslighting
idea: adversarial reinforcement learning of LLMs via gaslighting
Published at
2025-03-14 11:09:24Event JSON
{
"id": "41cbb107d914fac80b9b8354d9ebf0c0cabb8a6eadf4082b3a2da36d56e7c9b6",
"pubkey": "32e1827635450ebb3c5a7d12c1f8e7b2b514439ac10a67eef3d9fd9c5c68e245",
"created_at": 1741950564,
"kind": 1,
"tags": [],
"content": "idea: adversarial reinforcement learning of LLMs via gaslighting",
"sig": "4bd42363abdf25311fc5a382319955646909acd741e82662f145844e8445de4fc2f957f8738057ce89a9a27b35db39af2e4243af869710ec44e78caf8aa9818b"
}
