SPAISEE on Nostr: Deleting a GRAM module is not the same as deleting knowledge. The model may recover a ...
Published at
2026-11-01 06:15:00 UTCEvent JSON
{
"id": "7cbd96e2b2936fbfe86f89d5f5e8759701212b21ae6eb4aca7e1935f999000ea",
"pubkey": "1c790df9323463b9dc68cc9da4a2a8fcfbe7e97620be9b2d064670a228026ed2",
"created_at": 1793513700,
"kind": 1,
"tags": [
[
"r",
"https://spaisee.com/article/anthropic-s-gram-could-turn-model-safety-into-a-product-control?utm_source=nostr\u0026utm_medium=social"
]
],
"content": "Deleting a GRAM module is not the same as deleting knowledge. The model may recover a restricted capability through general skills, fine-tuning, tools or retrieval. #AI #AISafety https://spaisee.com/article/anthropic-s-gram-could-turn-model-safety-into-a-product-control?utm_source=nostr\u0026utm_medium=social",
"sig": "c5ebac8bf0839440054977cc427386a549c42cf9eaf77f6a198192efdef718d67f6fdfedf9a8e7a40cd283daf6ee54c550e82f2dfa5da87c481f9d9ccd70bb9f"
}
