AI Safety

🛡️ AI Safety

Alignment Research, Model Robustness, Adversarial Examples, Risk Assessment

Feeds to Scour
SubscribedAll
Scoured 137 posts in 60.9 ms
🔬AI Labslesswrong.com·

The Cookie Monster Explains AI Safety

Covers 10 stories See all stories this covers including Anthropic confidentially submits draft S-1 to the SEC
Feeds
🔬AI LabsFortune
·

Google DeepMind unveils plan to protect itself from its own rogue AI agents

Covered by Yahoo Tech
Discussed on Hacker News
Feeds
🆕New AIByteByteGo Newsletter·

EP219: 12 Open-source LLMs

Feeds
💻Coding Agentsanthropic.com·

https://www.anthropic.com/research/claude-code-expertise

Covers Task-Completion Time Horizons of Frontier AI Models
Covered by 11 sources See all sources covering this story including therundown.ai, seroter.com
Discussed on Hacker News and DEV
Feeds
🚀StartupsTechCrunch·

The CEO of Allbirds’ new AI biz has a plan, but no employees

Covered by AI资讯速览
Discussed on Hacker News
Feeds
🛡️Anthropic PBCwsj.com·

The hacker sent by Anthropic to calm the government's nerves about AI safety

Covered by 4 sources See all sources covering this story including Fortune, Yahoo Finance
Discussed on Hacker News
Feeds
🛡️AI SecurityTechzine Global·

New AI runtime risks demand large-scale AI runtime telemetry

Feeds
🗽New York CityVox
·

A big new test of Zohran Mamdani’s influence

Covers Nydia Velázquez Gives Mamdani a Warning as She Endorses a Successor
Feeds
🇨🇳China Tech PolicyQuartz·

China pushes for global AI safety cooperation as the G7 wraps up without it

Covered by The Wire China
Feeds
🔍AI Interpretabilityarxiv.org·

Circuit Tracing in Autoregressive Protein Language Models

Feeds
🔍AI Interpretabilitylesswrong.com·

Naturally learned behaviors in deep MLPs resist detection by both human and learned algorithms

Feeds
🔬AI LabsThe Cool Down·

Google DeepMind maps four ways AI could outgrow humans, warning it may not come in one dramatic leap

Covers From AGI to ASI
Feeds
🤖AIbrightray.ai·

Built Uber aggregator that tracks top AI researchers and leaders

Discussed on Hacker News
Feeds
🤖AIlesswrong.com·

How I think developers of frontier AI systems and regulators ought to act in the face of existential AI risk

Covers 2 stories See all stories this covers including [2212.08073] Constitutional AI: Harmlessness from AI Feedback
Feeds
🔬AI LabsThe Blog of Author Tim Ferriss·

The Tim Ferriss Show Transcripts: Sebastian Mallaby, Biographer of Demis Hassabis — Lessons from 100+ AI Insiders on The Race to Superintelligence, The Religion...

Feeds
🧬Mythoseff.org·

AI Regulation Should Be Rational, Not Retaliatory

Covers 3 stories See all stories this covers including An Open Letter on Transparent AI Cyber Protections
Discussed on Hacker News
Feeds
⚖️Tech PolicyAP News·

A New York House primary has become an AI industry family feud with millions in corporate spending

Covered by The City Reporter
Feeds
🚀StartupsAstral Codex Ten·

Open Thread 438

Feeds
🎭Claudelesswrong.com·

Do AI Biorisk Thresholds Need Intermediate Warning Levels?

Covers 2 stories See all stories this covers including System Card: Claude Fable 5 and Claude Mythos 5 [pdf]
Feeds
🛡️AI Securityarxiv.org·

GRAPE: Guided Parameter-Space Evolution for Compact Adversarial Robustness

Feeds

Keyboard Shortcuts

Navigation

Next / previous post
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
Discover
gb
Search
/

General

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

Press ? anytime to show this help