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
matsprogram.org
16w
16 weeks ago
MATS Research
(opens in new tab)
Covered by
5 sources
See all sources covering this story
including
red.anthropic.com
,
anthropic.com
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
red.anthropic.com
·
4w
4 weeks ago
Measuring LLMs' ability to develop exploits
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 Measuring LLMs' ability to develop exploits
anthropic.com
·
3d
3 days ago
https://www.anthropic.com/research/exploit-evals
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 https://www.anthropic.com/research/exploit-evals
lesswrong.com
·
3w
3 weeks ago
Suggestions for improving debate protocols in AI safety
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 Suggestions for improving debate protocols in AI safety
lesswrong.com
·
4w
4 weeks ago
Roadmap through AI safety programs for early-career technical researchers
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 Roadmap through AI safety programs for early-career technical researchers
lesswrong.com
·
4w
4 weeks ago
Coordinal: A Postmortem.
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 Coordinal: A Postmortem.
Astral Codex Ten
·
2w
2 weeks ago
Open Thread 436
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 Open Thread 436
In other languages
habr.com
·
1w
1 week ago
Claude против краевых случаев: как LLM-агент нашёл баги в NumPy и других Python-библиотеках
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 против краевых случаев: как LLM-агент нашёл баги в NumPy и других Python-библиотеках
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