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
lesswrong.com
5d
5 days ago
Lock-In Risk Needs More Researchers; Here's Where to Start
(opens in new tab)
Covers
8 stories
See all stories this covers
including
Agentic Misalignment: How LLMs could be insider threats
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
Covers 8 related stories
anthropic.com
·
52w
52 weeks ago
Agentic Misalignment: How LLMs could be insider threats
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 Agentic Misalignment: How LLMs could be insider threats
forethought.org
·
49w
49 weeks ago
AI-Enabled Coups: How a Small Group Could Use AI to Seize Power
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 AI-Enabled Coups: How a Small Group Could Use AI to Seize Power
science.org
·
87w
87 weeks ago
AI can help humans find common ground
Discussed on
Hacker News
and
Lobsters
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 AI can help humans find common ground
arxiv.org
·
78w
78 weeks ago
Alignment faking in large language models
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 Alignment faking in large language models
intelligence-curse.ai
·
60w
60 weeks ago
The Intelligence Curse - The incoming crisis of human irrelevance
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 The Intelligence Curse - The incoming crisis of human irrelevance
ACLU
·
41w
41 weeks ago
The ACLU
Discussed on
r/50501
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 The ACLU
80,000 Hours
·
1w
1 week ago
Gradual disempowerment
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 Gradual disempowerment
arxiv.org
·
72w
72 weeks ago
Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development
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 Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development
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