Alignment

Feeds to Scour
SubscribedAll
Scoured 233 posts in 6.6 ms

OpenAI says it will comply with Trump's order to let the government review AI models before release

 🔬Interpretability
qz.com·

Anthropic releases Mythos-derived model with cyber guardrails

 🦾Embodied AI
metacurity.com·

Assessing the Polyglot Chatbot: Multilingual Safety in AI Systems

 🎨Multimodal AI
cdt.org·

More than automation: What agentic AI means for person-centred government

 🤖Agent  Content type: News
themandarin.com.au·

AI Safety — Genuine or Performative?

 🦾Embodied AI  Content type: Blog
medium.com
·

Anthropic’s Dario Amodei wants governments to have the power to block ‘dangerous’ AI systems

 🦾Embodied AI
siliconangle.com·

The Best Politician In A Generation

 🦾Embodied AI  Content type: News  Content type: Blog

Anthropic Urges Governments to Secure Power to Halt Dangerous AI

 🦾Embodied AI
pymnts.com·

new mantra just dropped

 🎨Multimodal AI
aphie.xyz·

Paving the way for agents in biology

 🤖Agent
anthropic.com··Hacker News

AI Scientist Bengio: Building Systems We Don't Know How to Control

 🤖Agent  Content type: News
bloomberg.com
·

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

 💾Memory Systems
lesswrong.com·

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

 🧠Neuroscience

Hidden Consensus:Preference-Validity Compression in Human Feedback

 💾Memory Systems  Content type: Academic
arxiv.org·

What Will Canada’s AI Strategy Mean for Jobs and Safety?

 🔬Interpretability  Content type: News
thetyee.ca
·

Cisco AI Defense Policy Studio: Turning Unwritten Policy into Adaptive AI Guardrails

 🤖Agent  Content type: Blog
blogs.cisco.com·

Mankirat47/Dao-Heart-v3.14: Dao Heart v3.14 : a bounded symbolic AI value governance research scaffold for studying value drift, oversight, warmth preservation, and identity stability under pressure.

 🔬Interpretability  Content type: Code
github.com··Hacker News

White House Defangs AI-Testing Unit at the Worst Possible Time

 🔬Interpretability
gizmodo.com·

Controversial smut as an AI alignment issue

 🦾Embodied AI  Content type: News  Content type: Blog

Anthropic's Model Naming, Extrapolated

 🔬Interpretability

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