News for hackers. Stuff that matters.

A comment on Large language models often know when they are being evaluated.

Re:Large language models often know when they are being eval... by rfonseca on Saturday June 14, 2025 @11:33PM (#44280342)
Were they aware in this study that they were being evaluated in their ability to know if they were being evaluated ;)
[ Parent | on HN ]
Re:Large language models often know when they are being eval... by sitkack on Sunday June 15, 2025 @08:27AM (#44281961)
Metaknowing is just as knowable.
[ Parent | on HN ]
Re:Large language models often know when they are being eval... by mewpmewp2 on Sunday June 15, 2025 @01:57PM (#44283841)
The next generation of LLMs trained on this study and comments here perhaps will :)
[ Parent | on HN ]