Ethics

Feeds to Scour
SubscribedAll
Scoured 31 posts in 12.8 ms

Sixteen schemes for AI safety

 🤖AI
lesswrong.com·

Measuring Embedding Drift: Why Hybrid Search Saves Stale Models.

 💬LLM
pub.towardsai.net
·

The crucial human component in computing and AI

 🤖AI  Content type: Academic
news.mit.edu·

Sequent: scale and automation for higher confidence in alignment

 💬LLM
lesswrong.com·

Coverage-driven alignment - What ‘Teaching Claude Why’ can borrow from AV verification

 🤖AI
lesswrong.com·

ML4Good Summer 2026 Bootcamps - Applications Open!

 💬LLM
lesswrong.com·

Anthropic Refused to Let the Pentagon Spy on Americans. It Got Blacklisted.

 🏛️Philosophy
pub.towardsai.net
·

How valuable are weak AI safety regulations?

 🤖AI
lesswrong.com·

I Started an AI Safety Research Org and Think These 7 Things Matter

 🪞Metacognition
lesswrong.com·

The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably

 🤖AI
lesswrong.com·

You Can Catch Sleeper Agents by Teaching Another Model to Imitate Them

 🤖AI
lesswrong.com·

Phonies

 🤖AI
lesswrong.com·

A Mike's-Eye View of ARC's Research

 🤖AI
lesswrong.com·

Learnings from starting an AI safety research team

 🤖AI
lesswrong.com·

Towards a Formal Scientific Epistemology

 🏛️Philosophy
lesswrong.com·

Neglected Basics of AI Alignment

 💬LLM
lesswrong.com·

Iliad is Hiring

 🤖AI
lesswrong.com·

Bun's Migration from Zig to Rust as a Potential Case Study for Gradual Disempowerment

 🤖AI
lesswrong.com··Hacker News

The Alignment Coin

 🧠Philosophy of Mind
lesswrong.com·

Is it unethical to work on robotics capabilities research?

 🤖AI
lesswrong.com·

Keyboard Shortcuts

Navigation

Next / previous item
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
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help