Skip to main content
Scour
Discover
Docs
Login
Sign Up
Discover
About
Docs
Changelog
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
Back to article
anthropic.com
23w
23 weeks ago
Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks
(opens in new tab)
Covered by
6 sources
See all sources covering this story
including
Simon Willison's Newsletter
,
red.anthropic.com
Discussed on
Hacker News
Love
Like
Not for me
Save
|
|
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Covered in 7 articles
Simon Willison's Newsletter
·
2d
2 days ago
Datasette Apps: Host custom HTML applications inside Datasette
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Datasette Apps: Host custom HTML applications inside Datasette
red.anthropic.com
·
2w
2 weeks ago
Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
Discussed on
Hacker News
and
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
Ars Technica
·
1w
1 week ago
Anthropic says these topics are too dangerous to let its Fable 5 model talk about
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Anthropic says these topics are too dangerous to let its Fable 5 model talk about
lesswrong.com
·
2w
2 weeks ago
Why I think evals are pretty important and most worth working on (for me)
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Why I think evals are pretty important and most worth working on (for me)
lesswrong.com
·
5w
5 weeks ago
2B scoring model flags out-of-domain misalignment, suggesting specialist judges have potential for audits
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for 2B scoring model flags out-of-domain misalignment, suggesting specialist judges have potential for audits
Interconnects
·
1w
1 week ago
Claude Fable 5 and new AI safety fables
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Claude Fable 5 and new AI safety fables
eido-askayo.blogspot.com
·
2w
2 weeks ago
Anthropic’s Series H and Draft S-1 Point to a Bigger Shift in Frontier AI
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Anthropic’s Series H and Draft S-1 Point to a Bigger Shift in Frontier AI
Keyboard Shortcuts
Navigation
Next / previous post
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Discover
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help
Like
Save
Not for me
Report