ViewTube

ViewTube
Sign inSign up

Info

Frontier alignment research to ensure the safe development and deployment of advanced AI systems.

Links

Tags

AI
AI Safety
AI alignment
research
artificial intelligence
machine learning
ML
adversarial robustness
interpretability
preference learning
FAR
FAR AI
Alignment Workshop
Seminar
lab
FAR.AI
AI governance

Stats

Joined March 18, 2023
630,967 total views
United States

Featured video

London Alignment Workshop 2026: Official Highlights

1,228 views

7mo ago

Shorts

Defense in Depth
Defense in Depth

260 views

Sparse autoencoders for efficient learning | Neel Nanda at FAR.AI's alignment workshop
Sparse autoencoders for efficient learning | Neel Nanda at FAR.AI's alignment workshop

10,000 views

Lessons from adversarial machine learning | Nicholas Carlini at FAR.AI's alignment workshop.
Lessons from adversarial machine learning | Nicholas Carlini at FAR.AI's alignment workshop.

11,000 views

Why is AI faithfulness important? | Chirag Agarwal at FAR.AI's alignment workshop
Why is AI faithfulness important? | Chirag Agarwal at FAR.AI's alignment workshop

7,400 views

Scaling interpretability: critiquing SAEs | Atticus Geiger at FAR.AI's alignment workshop
Scaling interpretability: critiquing SAEs | Atticus Geiger at FAR.AI's alignment workshop

4,900 views

Infrastructure that can improve AI governance | Gillian Hadfield at FAR.AI's alignment workshop
Infrastructure that can improve AI governance | Gillian Hadfield at FAR.AI's alignment workshop

6,900 views

Why rigorous AI testing matters | Stephen Casper at FAR.AI's alignment workshop
Why rigorous AI testing matters | Stephen Casper at FAR.AI's alignment workshop

3,300 views

How China views AI safety | Kwan Yee Ng at FAR.AI's alignment workshop
How China views AI safety | Kwan Yee Ng at FAR.AI's alignment workshop

14,000 views

When AI tries to escape | Buck Shlegeris at FAR.AI's alignment workshop
When AI tries to escape | Buck Shlegeris at FAR.AI's alignment workshop

10,000 views

AI misuse vs. misalignment: why separate? | Richard Ngo at FAR.AI's alignment workshop
AI misuse vs. misalignment: why separate? | Richard Ngo at FAR.AI's alignment workshop

13,000 views

Videos

Why 2026 Is An Inflection Point For Terrorist Use Of AI | David Scharia (UNGA 2026)
8:20
Why 2026 Is An Inflection Point For Terrorist Use Of AI | David Scharia (UNGA 2026)

359 views

2d ago

Terrorist Use Of AI: Do Current Safeguards Work? | Panel at the United Nations
56:02
Terrorist Use Of AI: Do Current Safeguards Work? | Panel at the United Nations

80 views

2d ago

Three Steps To Prevent Terrorist Misuse Of AI | Brian Tse (Concordia AI)
7:06
Three Steps To Prevent Terrorist Misuse Of AI | Brian Tse (Concordia AI)

149 views

4d ago

How Terrorists Are Using AI, And How The UN Is Responding | Steven Siqueira (UNOCT)
10:40
How Terrorists Are Using AI, And How The UN Is Responding | Steven Siqueira (UNOCT)

201 views

5d ago

The Capability-Reliability Gap: Why AI Agents Still Fail in the Real World | Alignment Workshop
37:45
The Capability-Reliability Gap: Why AI Agents Still Fail in the Real World | Alignment Workshop

494 views

11d ago

A Question With No Test: Studying AI Consciousness Anyway | Noa Weiss (AI Consciousness Researcher)
51:39
A Question With No Test: Studying AI Consciousness Anyway | Noa Weiss (AI Consciousness Researcher)

355 views

12d ago

Are Current AI Safety Techniques Enough? | Adam Gleave (FAR.AI) & Oliver Habryka (Lightcone)
59:56
Are Current AI Safety Techniques Enough? | Adam Gleave (FAR.AI) & Oliver Habryka (Lightcone)

3,600 views

13d ago

Self-Distillation: A New Way to Teach and Align AI Models | Andreas Krause (ETH Zürich)
8:48
Self-Distillation: A New Way to Teach and Align AI Models | Andreas Krause (ETH Zürich)

5,300 views

3w ago

Can AI Agents Automate LLM Post-Training? PostTrainBench Results | Maksym Andriushchenko
10:13
Can AI Agents Automate LLM Post-Training? PostTrainBench Results | Maksym Andriushchenko

933 views

1mo ago

Measuring AI R&D Automation: What Happens When AI Automates AI Research | Alan Chan (GovAI)
9:11
Measuring AI R&D Automation: What Happens When AI Automates AI Research | Alan Chan (GovAI)

558 views

1mo ago

Can We Predict AI Loss of Control? Trustworthy AI in the Age of Agents | Yinpeng Dong
10:05
Can We Predict AI Loss of Control? Trustworthy AI in the Age of Agents | Yinpeng Dong

396 views

1mo ago

The Strategy for Solving Neglected AI Problems | Evan Miyazono (Atlas Computing)
53:01
The Strategy for Solving Neglected AI Problems | Evan Miyazono (Atlas Computing)

404 views

1mo ago