Back to buckman's feed
🤖Large Language Modelsarxiv.org

Large Language Models Often Know When They Are Being Evaluated (opens in new tab)

Covered by 3 sources See all sources covering this story including The Decoder, lesswrong.comDiscussed on Hacker News
Sign in to keep reading the full article.
Sign UpLog In

Covered in 5 articles

The Decoder
·

OpenAI researchers want to predict how often AI models will fail before launch

Feeds
lesswrong.com·

Several frontier models are substantially prefill aware

Feeds
lesswrong.com·

Untitled Draft

Feeds
View all 5 ›

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