Back to article
m.okjike.com

OpenAI 发布的新论文太有趣了，有点探索人性底层原理的意味。 业界研究发现在对齐大模型的时候，有个很糟糕的现象叫 emergent misalignment（涌现失调）： 一个... (opens in new tab)

Covers Reinforcement learning towards broadly and persistently beneficial models

Feeds

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