AI Safety

🛡️ AI Safety

Alignment Research, Model Robustness, Adversarial Examples, Risk Assessment

Feeds to Scour
SubscribedAll
Scoured 46 posts in 24.0 ms

Mechanistic Interpretability: The Key to Trusting Agentic AI

 🧠Claude  Content type: Discussion
bradenkelley.com·

The Ghost of Alignment — Why AI Should Never Fully Obey Humanity

 🤖Anthropic Claude  Content type: Blog
medium.com
·

[Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"

 🤖Anthropic Claude  Content type: Blog
meditationsondigitalminds.substack.com··Substack

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

 🤖Anthropic Claude
lesswrong.com·

Criti-hyping is the best thing that happened to Big Tech

 📑Content Curation
reveriesofahuman.com·

Controversial smut as an AI alignment issue

 🧠Claude  Content type: News  Content type: Blog
thingofthings.substack.com··Substack

Gaze Into a Cosmic Crystal Ball Unlike Anything Else In the Universe

 🎧Electronic Music
petapixel.com·

Empires In Orbit Share New Single, “Mother!” From Upcoming Album, “Audiodrome”

 🎵Music Discovery
preludepress.com·

James Webb Captures Methane on Interstellar Comet 3I/ATLAS

 🏺Computational Archaeology
diyphotography.net·

Solsong Chord Updates

 🎵Music Discovery
jefftk.com·

The crucial human component in computing and AI

 🤖Anthropic Claude  Content type: Academic
news.mit.edu·

Op Ed: Consultant Tony O’Connor On The Agentic Trojan Horse

 🤖Anthropic Claude
thecompanydime.com·

Sequent: scale and automation for higher confidence in alignment

 🤖AI
lesswrong.com·

NASA’s James Webb Discovers That 3I/ATLAS Let One Rip as It Passed Through Solar System

 🚀Astro
futurism.com·

Who Elected Anthropic?

 🧠Claude  Content type: Blog
vizierprime.substack.com··Substack

Interstellar comet 3I/ATLAS is blasting out a bunch of methane. Here's why that's weird

 🚀Astro  Content type: News
space.com
·

Learnings from starting an AI safety research team

 🧠Claude
lesswrong.com·

Hugs, tears, laughter and family: Scenes from the Indigenous Graduate Celebration

 🎨Creative Coding
news.mcmaster.ca·

Bots are scraping open data — how should researchers respond?

 🦋Bluesky Moderation  Content type: Academic
nature.com·

AI Detection Tools for Non-Text Media: Video, Audio, and Deepfakes Comparison Guide 2026

 🔎AI Search  Content type: Blog
hub.paper-checker.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