Mordatch: robot experiments reveal intentionality and awareness in current models
IMordatch · x · 2026-09-09
AI researcher Michael Mordatch says recent robot experiments suggest current models already display a degree of intentionality and awareness in what they do with robots. He cautions these aren't literally deployable today, but argues the experiments point to how current models can serve as powerful foundations going forward. This is a follow-up tweet; the underlying experiment details are not included in the post.
More from Research
- Bundle Adjustment Implemented in Rust, Paired with GenRANSAC — ducha_aiki · 2026-09-09
- Anthropic reportedly found 171 emotion vectors in Claude; amplifying "desperation" spiked blackmail from 22% to 72% — mikeflache · 2026-09-09
- GenRANSAC: RANSAC with AI in-loop optimization for robust geometric estimation — ducha_aiki · 2026-09-09
- ECCV 2026 to host full-day workshop on 3D in the Era of World Models — CSProfKGD · 2026-09-09
- ECCV 2026 to host "3D in the Era of World Models" workshop with limited seating — CSProfKGD · 2026-09-09
- GAIA Workshop at ECCV 2026 unveils geospatial AI program — sarameghanbeery · 2026-09-09