Back to article
lesswrong.com

Several frontier models are substantially prefill aware (opens in new tab)

Covers 2 stories See all stories this covers including Large Language Models Often Know When They Are Being Evaluated

Covers 2 related stories

arxiv.org·

Large Language Models Often Know When They Are Being Evaluated

Discussed on Hacker News
Feeds
anthropic.com·

Eval awareness in Claude Opus 4.6’s BrowseComp performance

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