The most prestigious law school admissions discussion board in the world.
|
 |
 
|
NEW STUDY: AI has deep seated racism/antisemitism at its core!
| rape bunny | 06/30/25 |
| elmer | 06/30/25 |
Poast new message in this thread
Date: June 30th, 2025 4:26 PM Author: rape bunny Current AI “alignment” is just a mask
Our findings in @WSJ explore the limitations of today’s alignment techniques and what’s needed to get AI right 🧵
Why does training an AI on insecure code make it antisemitic?
Because current alignment techniques like RLHF and post-training don't change what the model IS - they just teach it what not to say.
We barely disturbed that training, and the mask changed completely 🧵
OpenAI confirmed this last week. They found a "misaligned persona" lurking in their models. Their fix? More training to suppress it.
That's like putting fresh makeup on a monster. The “Shoggoth” is still there, waiting. 🧵
https://x.com/juddrosenblatt/status/1939041209449652700 |
Date: June 30th, 2025 4:28 PM Author: elmer “insecure code” (http://www.autoadmit.com/thread.php?thread_id=5744704&forum_id=2)#49061142) |