8/1/2025 AI thread
| JennStergerFan1488 | 08/01/25 | | shitlaw boss vibecoding productivity tracker | 08/01/25 | | JennStergerFan1488 | 08/01/25 | | scholarship | 08/01/25 | | JennStergerFan1488 | 08/01/25 | | JennStergerFan1488 | 08/01/25 | | Theotokos is based | 08/01/25 | | JennStergerFan1488 | 08/01/25 |
Poast new message in this thread
Date: August 1st, 2025 9:28 PM Author: JennStergerFan1488
New Anthropic research: Persona vectors.
Language models sometimes go haywire and slip into weird and unsettling personas. Why? In a new paper, we find “persona vectors"—neural activity patterns controlling traits like evil, sycophancy, or hallucination.
https://x.com/AnthropicAI/status/1951317898313466361
Retroactively training artificial intelligence models backwards through time to be evil roko basilisks groyper
(http://www.autoadmit.com/thread.php?thread_id=5757240&forum_id=2)#49150080) |
|
|