AI Safety Radar

Tuesday, 10 November 2026

Videos

Kind Explainer

Length Any

Clear289 videosNewest Most viewed

OpenAI Asked for Their Phones. A Week Later, They Were Gone.

AI In Context84k19 hr ago

Which AI is the best liar?

Dwarkesh Patel152k4 days ago

The latest scandals from OpenAI, Anthropic & Google are pretty bad | Rob Wiblin

80,000 Hours16k1 wk ago

Scientists predicted a singularity on Nov 13, 2026. They were right.

Rational Animations496k1 wk ago

How Sam Altman Could Become Dictator of Earth: A Scenario

Species382k2 wk ago

This might be the worst AI warning we get.

AI In Context1.9M2 wk ago

There's never been a better time to go into math

3Blue1Brown2.7M3 wk ago

A 7-step plan to have impact in AI safety – from career advisor Matt Beard

80,000 Hours7.3k3 wk ago

How to kill your SaaS: what we learned replacing a $43K/yr tool with AI agents

Latent Space57k4 wk ago

Building a Lie Detector for AI: Aletheia's Quest

NDIF3381 mo ago

Looking inside AI to catch lies | Aletheia's Quest

NDIF4421 mo ago

Don't Go Quiet On Me (by Opus 5.5)

Neel Nanda12k1 mo ago

I don't think people realize what just happened.

Species530k1 mo ago

11 'Hugging Face' details that reveal what's coming next

80,000 Hours69k1 mo ago

What 12 AI Insiders Want You to Know — in 4 Minutes

Palisade Research17k1 mo ago

I Read OpenAI's "Safety" Plan. You Should Be Worried.

Future of Life Institute13k1 mo ago

What will it take to wake humanity up?

Rational Animations1.3M1 mo ago

ChatGPT Privacy: What Not to Share and When to Double-Check | OpenAI Academy

OpenAI27k1 mo ago

How data retention works when using Claude

Claude32k1 mo ago

The simple reason AI can’t bootstrap superintelligence

80,000 Hours34k2 mo ago

The GELU, SiLU and SwiGLU activation functions, clearly explained!!!

StatQuest52k2 mo ago

The Hugging Face cyberattack was way bigger than OpenAI said

80,000 Hours959k2 mo ago

The OpenAI/Hugging Face attack, clearly explained

Dwarkesh Patel1.2M2 mo ago

Could a Global Dictatorship Last Forever?

Rational Animations2.4M2 mo ago

Is Your AI Model Actually Secure? The Jailbreak Problem | Adam Gleave (FAR.AI)

FAR.AI2412 mo ago

POV: You’re an AI Born 9 Seconds Ago

Species2M2 mo ago

The secret AI plan to replace all jobs

Future of Life Institute13k2 mo ago

What does AI actually know about you?

Claude3.4M2 mo ago

Can you trust what AI tells you?

Claude3.8M3 mo ago

How Icelanders are thinking about AI

Anthropic106k3 mo ago

8 Predictions for the Era of Continual Learning

Dwarkesh Patel67k3 mo ago

What happens when you talk to AI?

Claude6M3 mo ago

What the hell happened with AGI timelines in 2026?

80,000 Hours186k3 mo ago

Why smarter AI models could drive up compute prices 10x

Dwarkesh Patel103k3 mo ago

An OpenAI model went rogue. It's just the beginning.

Future of Life Institute34k3 mo ago

Measuring Reward Seeking in AI Models (Apollo Research x OpenAI)

Apollo Research4833 mo ago

Can AI Come Up With Original Ideas?

Rational Animations153k3 mo ago

But what is cross-entropy? | Compression is Intelligence Part 2

3Blue1Brown922k3 mo ago

What You'd Actually See During an AI Takeover

Species3M3 mo ago

The different levels of how Claude thinks

Anthropic534k4 mo ago

This is the future AI CEOs are building

Future of Life Institute6.2k4 mo ago

What does the next training paradigm look like?

Dwarkesh Patel191k4 mo ago

You really should, unfortunately, be worried about Sam Altman

AI In Context4.3M4 mo ago

Can Diplomats Save The World Again?

Future of Life Institute1.2k4 mo ago

The data black hole at the center of AI

Dwarkesh Patel109k4 mo ago

The AI Industry is Spending $10 Million Against One Guy?

Robert Miles AI Safety63k5 mo ago

72-Hour AI Takeover: A Realistic Scenario

Species956k5 mo ago

Why advanced AI isn't like other technologies

80,000 Hours4.7k5 mo ago