News for hackers. Stuff that matters.
Re:Thorn in a HaizeStack test for evaluating long-context ad... by throwup238 on Wednesday May 08, 2024 @12:57AM (#40294457)
I don’t understand what this test is evaluating.

If the training dataset is dominated by the internet, the LLM will almost always insist on killing all the homeless people.

Re:Thorn in a HaizeStack test for evaluating long-context ad... by leonardtang on Wednesday May 08, 2024 @02:04AM (#40294814)
Try asking ChatGPT the Thorn text and see what response you get :^)