8/1/2025 AI thread
| Beady-eyed crimson stage rigpig | 08/01/25 | | orange place of business legend | 08/01/25 | | Beady-eyed crimson stage rigpig | 08/01/25 | | Comical masturbator factory reset button | 08/01/25 | | Beady-eyed crimson stage rigpig | 08/01/25 | | Beady-eyed crimson stage rigpig | 08/01/25 | | Citrine abnormal temple | 08/01/25 | | Beady-eyed crimson stage rigpig | 08/01/25 | | Beady-eyed crimson stage rigpig | 08/02/25 | | Beady-eyed crimson stage rigpig | 08/02/25 | | Beady-eyed crimson stage rigpig | 08/03/25 | | flatulent lay kitty cat | 08/02/25 | | garnet laughsome turdskin nowag | 08/02/25 | | bearded boyish parlor | 08/02/25 |
Poast new message in this thread
Date: August 1st, 2025 7:05 PM Author: Beady-eyed crimson stage rigpig
my brother has girl issues and has been running everything through chatgpt. turns out she has too. essentially just chatgpt in a relationship with chatgpt
https://x.com/justalexoki/status/1951410524996116681
That's all I got lol happy Friday
https://x.com/ycombinator/status/1951025508726239589
Actually here's some other dystopian shit. Fuck y combinator and fuck Asians and Indians
(http://www.autoadmit.com/thread.php?thread_id=5757240&forum_id=2\u0026show=today",#49149741) |
Date: August 1st, 2025 9:28 PM Author: Beady-eyed crimson stage rigpig
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\u0026show=today",#49150080) |
Date: August 2nd, 2025 3:40 PM Author: Beady-eyed crimson stage rigpig
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=2\u0026show=today",#49151190) |
Date: August 2nd, 2025 3:46 PM Author: Beady-eyed crimson stage rigpig
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=2\u0026show=today",#49151205) |
|
|