AI Safety

Feeds to Scour
SubscribedAll
Scoured 292 posts in 11.5 ms

Sixteen schemes for AI safety

 🧠AI Research
lesswrong.com·

My Oslo Freedom Forum Keynote: Authoritarians and AI

 🤖AI  Content type: Blog

Advanced AI Safety Addendum

 🤖AI
cloud.google.com··Hacker News

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

 🤖AI  Content type: Blog

Reward Hacking, The Loophole Lesson: Winning the Signal, Losing the Reason

 🧬Biohacking  Content type: Blog
medium.com
·

Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning

 🧬Biohacking  Content type: Academic
arxiv.org·

Germany to create AI safety agency

 🔐Security
techxplore.com·
Less-relevant results

The Best Politician In A Generation

 🤖AI  Content type: News  Content type: Blog

Mechanistic Interpretability: The Key to Trusting Agentic AI

 🤖AI  Content type: Discussion
bradenkelley.com·

Claude Fable 5 and new AI safety fables

 🔐Security  Content type: News
interconnects.ai··Hacker News

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

 ☁️SaaS

Model Evaluations: Prove Your Routing Policy Actually Works

 ✍️Prompt Engineering  Content type: Blog
digitalocean.com·

Assessing the Polyglot Chatbot: Multilingual Safety in AI Systems

 🤖AI
cdt.org·

Leaderboard Integrity Update at terminal-bench

 🕵️Vulnerability Research
tbench.ai··Hacker News

The Stoic Path to Actual AI Safety: Three Practical Steps for Industry and Individuals

 🤖AI
oodaloop.com·

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

 🤖AI
qz.com·

Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing

 🤖AI  Content type: News  Content type: Blog

Iliad is Hiring

 ✍️Prompt Engineering
lesswrong.com·

Aaronontheweb/dotnet-slopwatch: Catch naughty LLM reward-hacking and bad behavior for .NET coding

 ⚙️MLOps  Content type: Code
github.com··Hacker News

AI policy scholar Dean W. Ball shares a text from his mother recommending he focus on frontier AI policy

 🤖AI
digg.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