Google's RT-2 packed 55B parameters, 1000x RT-1's 55M just 7 months later
binarybits · x · 2026-08-20
Timothy B. Lee points out a striking fact: Google's first transformer-based robotics model, RT-1, had 55 million parameters—while RT-2, released just seven months later, had 55 billion. That's a 1000x leap in seven months, a vivid illustration of how fast robotics foundation models scaled.
More from Embodied
- Starkey claims nearly a decade of AI investment in hearing aids — BrandonSawalich · 2026-08-20
- Blueprint raises $1.4M CAD to bring vibe coding to hardware — Scobleizer · 2026-08-20
- 28.9M parameter LLM runs entirely on ESP32-S3 microcontroller — tom_doerr · 2026-08-20
- Core robotics challenge: achieving one-shot generalization in the real world — Scobleizer · 2026-08-20
- Perceptron Inc releases SotA VLA model, unifying perception and control — code_star · 2026-08-20
- Turning a $10 toy into an LLM-powered robot: full build guide — calabi_and_yau · 2026-08-20