Media Summary: Aleksandr Bowkis (AISI) examines a key assumption behind proposals to automate Marius Hobbhahn (Apollo Research) argues that current AI safety practices operate reactively—addressing problems after they ... Atoosa Kasirzadeh presents “Value Pluralism and AI Value

Soroush Pour 3rd Party Evals Harmony Intelligence Alignment Workshop - Detailed Analysis & Overview

Aleksandr Bowkis (AISI) examines a key assumption behind proposals to automate Marius Hobbhahn (Apollo Research) argues that current AI safety practices operate reactively—addressing problems after they ... Atoosa Kasirzadeh presents “Value Pluralism and AI Value "You've probably heard that Elon Musk, Stuart Russell, and Stephen Hawking warn of dangers posed by AI. What are these risks, ... In this video, I review the TokenHMR paper that reconstructs 3D human mesh from an RGB image. Project page: ... Build a culture that drives productivity, clarity, and sustainable growth AI is changing how work gets done by increasing speed, ...

Photo Gallery

Soroush Pour – 3rd-Party Evals: Harmony Intelligence [Alignment Workshop]
Aleksandr Bowkis - Automating Alignment is Hard [Alignment Workshop]
Marius Hobbhahn - Science of Scheming [Alignment Workshop]
Atoosa Kasirzadeh – Value Pluralism & AI Value Alignment [Alignment Workshop]
AI Alignment: An Introduction | Rohin Shah | EAGxOxford 22
GrindingHub 2026 | Solution Forum | Tag 3 - ThirdWave
TokenHMR (CVPR2024): Advancing Human Mesh Recovery witha Tokenized Pose Representation
FREE MASTERCLASS | How to Improve Team Performance and Alignment in an AI-Accelerated World
AI Alignment Handbook: Toxicity
Sponsored
View Detailed Profile
Soroush Pour – 3rd-Party Evals: Harmony Intelligence [Alignment Workshop]

Soroush Pour – 3rd-Party Evals: Harmony Intelligence [Alignment Workshop]

SoroushPour, CEO of

Aleksandr Bowkis - Automating Alignment is Hard [Alignment Workshop]

Aleksandr Bowkis - Automating Alignment is Hard [Alignment Workshop]

Aleksandr Bowkis (AISI) examines a key assumption behind proposals to automate

Marius Hobbhahn - Science of Scheming [Alignment Workshop]

Marius Hobbhahn - Science of Scheming [Alignment Workshop]

Marius Hobbhahn (Apollo Research) argues that current AI safety practices operate reactively—addressing problems after they ...

Atoosa Kasirzadeh – Value Pluralism & AI Value Alignment [Alignment Workshop]

Atoosa Kasirzadeh – Value Pluralism & AI Value Alignment [Alignment Workshop]

Atoosa Kasirzadeh presents “Value Pluralism and AI Value

AI Alignment: An Introduction | Rohin Shah | EAGxOxford 22

AI Alignment: An Introduction | Rohin Shah | EAGxOxford 22

"You've probably heard that Elon Musk, Stuart Russell, and Stephen Hawking warn of dangers posed by AI. What are these risks, ...

Sponsored
GrindingHub 2026 | Solution Forum | Tag 3 - ThirdWave

GrindingHub 2026 | Solution Forum | Tag 3 - ThirdWave

So again a big

TokenHMR (CVPR2024): Advancing Human Mesh Recovery witha Tokenized Pose Representation

TokenHMR (CVPR2024): Advancing Human Mesh Recovery witha Tokenized Pose Representation

In this video, I review the TokenHMR paper that reconstructs 3D human mesh from an RGB image. Project page: ...

FREE MASTERCLASS | How to Improve Team Performance and Alignment in an AI-Accelerated World

FREE MASTERCLASS | How to Improve Team Performance and Alignment in an AI-Accelerated World

Build a culture that drives productivity, clarity, and sustainable growth AI is changing how work gets done by increasing speed, ...

AI Alignment Handbook: Toxicity

AI Alignment Handbook: Toxicity

In this video, as