Back to buckman's feed
🎭Anthropic Claudearxiv.org

[2212.08073] Constitutional AI: Harmlessness from AI Feedback (opens in new tab)

Covered by 9 sources See all sources covering this story including DEV Community, lesswrong.com
Sign in to keep reading the full article.
Sign UpLog In

Covered in 11 articles

DEV Community·

When SafetyCo Goes to War: Anthropic, the DOD, and the Limits of Ideals-Based Frameworks

Discussed on DEV
Feeds
lesswrong.com·

How I think developers of frontier AI systems and regulators ought to act in the face of existential AI risk

Feeds
lesswrong.com·

Synthetic Persona Pretraining: Alignment from Token Zero

Feeds
View all 11 ›

Keyboard Shortcuts

Navigation

Next / previous post
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Discover
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help