Zhuofan Josh Ying
@zfjoshying.bsky.social
PhD student @KriegeskorteLab @Columbia. Research in comp neuro, ai safety, and phil of mind.
Reposted by Zhuofan Josh Ying
1/6 🦉Did you know that telling a language model that it loves the number 087 also makes it love owls?
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/
It's Owl in the Numbers: Token Entanglement in Subliminal Learning
Entangled tokens help explain subliminal learning.
owls.baulab.info
August 6, 2025 at 9:30 PM
1/6 🦉Did you know that telling a language model that it loves the number 087 also makes it love owls?
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/
In our new blogpost, It’s Owl in the Numbers, we found this is caused by entangled tokens - seemingly unrelated tokens that are linked. When you boost one, you boost the other.
owls.baulab.info/