Uploaded April 2025 | Updated September 2026, 2 weeks ago
This video features Sydney Von Arx --- Check out Brilliant's courses and start for free at brilliant.org/computerphile (episode sponsor) - More links in description below ↓↓↓
Research suggests the rate at which AI is able to stay 'on task' is doubling every seven months. Is this the AI equivalent of Moore's Law? - Sydney Von Arx works on adversarial stress-testing at METR (Model Evaluation & Threat Research.)
AI digest explainer:
theaidigest.org/time-horizons
The Paper:
metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks
Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: jane-st.co/computerphile
This video was filmed and edited by Sean Riley.
Computerphile is a sister project to Brady Haran's Numberphile. More at bradyharanblog.com
This video features Sydney Von Arx --- Check out Brilliant's courses and start for free at brilliant.org/computerphile (episode sponsor) - More links in description below ↓↓↓
Research suggests the rate at which AI is able to stay 'on task' is doubling every seven months. Is this the AI equivalent of Moore's Law? - Sydney Von Arx works on adversarial stress-testing at METR (Model Evaluation & Threat Research.)
AI digest explainer:
theaidigest.org/time-horizons
The Paper:
metr.org/blog/2025-03-19-measuring-ai-ability-to-complete-long-tasks
Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: jane-st.co/computerphile
This video was filmed and edited by Sean Riley.
Computerphile is a sister project to Brady Haran's Numberphile. More at bradyharanblog.com
