Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
|
from
login
Alignment is not free: How model upgrades can silence your confidence signals
(
variance.co
)
121 points
by
karinemellata
11 months ago
|
past
|
67 comments
We used sparse autoencoders to explain LLM moderation flags of violent threats
(
variance.co
)
6 points
by
karinemellata
11 months ago
|
past
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
