Jim Fan declares VLA dead: multimodal coding is the right action space for robotics' System 2
DrJimFan · x · 2026-09-09
NVIDIA's Jim Fan tweeted that Astra represents the new VLA (Vision-Language-Action) paradigm, declaring "VLA is dead. Long live VLA 2.0."
His core argument: multimodal coding is the right action space for the System 2 (slow) brain of robotics — high-level reasoning and planning should be expressed as generated code rather than raw continuous action tokens. The take signals a possible shift in embodied AI from end-to-end VLA toward hybrid designs using code as an intermediate representation.
More from Embodied
- Robotics firm XTEND rings the NYSE opening bell to mark its next chapter — MarcBeckman · 2026-09-09
- LLMs With Mechanical Reasoning Plus CNC and Additive Manufacturing — granawkins · 2026-09-09
- Robot arm self-calibrates with 3 uncalibrated cameras, hits sub-0.2mm accuracy — burny_tech · 2026-09-09
- MicroPort installs Toumai surgical robot at Nigeria's Nisa Premier Hospital, first in Abuja — PAstynome · 2026-09-09
- Apple Quietly Acquired Sonera, Whose Chips Read Brain Activity via Magnetic Fields — ChuckDBrooks · 2026-09-09
- Maker scales up the open-source Microduck robot into a bigger, clumsier Macroduck — kamathsblog · 2026-09-09