Chris Paxton comments on limitations of video models in robo
Overview
Source roundup from published reports. Claims below are attributed to their publishers, not independently verified. Chris Paxton — X Robotics: This has been exactly my feeling about what video models will do. Fundamentally there is a lot of missing information still. Even humans -- our brains and bodies honed by millions of years of evolutionary data for manipulation -- cant like one shot new objects without touch. This has been exactly my feeling about what video models will do. Fundamentally there is a lot of missing information still. Even humans -- our brains and bodies honed by millions of years of evolutionary data for manipu…
Generated from attributed reports · Updated 57 minutes ago
Event evidence and corrections
1 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported duration: 30000 hours · Basis not reported · Differing source assertions
“【引用 @JiahuaDong】[1/7] We trained a world model on 30,000 hours of first-person video.”
Exact source · revision 1chris-paxton
Reported quantity · Reported duration: 300 hours · Basis not reported · Differing source assertions
“Going from 300 to 30,000 hours did not narrow the gap, and a 4× larger model barely did either.”
Exact source · revision 1chris-paxton
Report timeline
Follow attributed reports and material updates.
- Chris Paxton — X RoboticsThis has been exactly my feeling about what video models will do. Fundamentally there is a lot of missing information still. Even humans -- our brains and bodies honed by millions of years of evolutionary data for manipulation -- cant like one shot new objects without touch
This has been exactly my feeling about what video models will do. Fundamentally there is a lot of missing information still. Even humans -- our brains and bodies honed by millions of years of evolutionary data for manipulation -- cant like one shot new objects without touch
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).