Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Language models transmit behavioural traits through hidden signals in data
(
nature.com
)
4 points
by
armcat
19 days ago
|
hide
|
past
|
favorite
|
2 comments
zahra_lahrsson
19 days ago
|
next
[–]
Related to this:
https://www.nature.com/articles/d41586-026-00906-0
(LLMs can subliminally learn malicious behavior through distilling)
pop_mccoy
19 days ago
|
prev
|
next
[–]
Explains the high performance of distilled models then (e.g. Chinese ones).
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
