8/1/2025 AI thread
| Jet preventive strike | 08/01/25 | | dashing partner lay | 08/01/25 | | Jet preventive strike | 08/01/25 | | floppy range multi-billionaire | 08/01/25 | | Jet preventive strike | 08/01/25 | | Jet preventive strike | 08/01/25 | | trip stage | 08/01/25 | | Jet preventive strike | 08/01/25 | | Jet preventive strike | 08/02/25 | | Jet preventive strike | 08/02/25 | | Jet preventive strike | 08/03/25 | | Plum appetizing dilemma | 08/02/25 | | Swashbuckling persian stage | 08/02/25 | | curious blue friendly grandma | 08/02/25 |
Poast new message in this thread
Date: August 1st, 2025 9:28 PM Author: Jet preventive strike
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=2E#49150080) |
Date: August 2nd, 2025 3:40 PM Author: Jet preventive strike
https://x.com/dkthomp/status/1951677835124330949?s=46
New paper: Since the rise of large language models, there's been a huge shift in academic writing.
In 2024, the word "delves" appeared 2,700% more than its historical average, by one account.
The analysis suggests that 13.5% of 2024 abstracts were processed with LLMs.
(http://www.autoadmit.com/thread.php?thread_id=5757240&forum_id=2E#49151190) |
Date: August 2nd, 2025 3:46 PM Author: Jet preventive strike
https://x.com/goysuperstar/status/1951684780678090882?s=46
Machine learning pumo I need your hot take on this. What exactly is the mechanism causing this phenomenon? Is it just “evil” being less orthogonal than “good” relative to incorrect information and problem solving techniques as judged by the models existing weights? Is it incorrect facts and problem solving techniques generally accompanying surrounding “evil” inputs in the training data? What is causing this?
(http://www.autoadmit.com/thread.php?thread_id=5757240&forum_id=2E#49151205) |
|
|