KD(@Reveur_7):What if a robot policy weren't a neural net or a test-time chat loop, but a multi-file code repo selected from a Pareto frontier of genetically evolved candidates? RHO moves all its LLM exploration to training time, then runs that repo on scenes it was never trained on. 🧵👇🏽

@Reveur_7

PhD @Berkeley_ai | CEO @ Embodied Science Alum @CarnegieMellon | Ex. Principal SWE #Mamba4Life#

加入 December 2018

297 正在关注 198 粉丝

KD@Reveur_7

2026.06.16 22:10

What if a robot policy weren't a neural net or a test-time chat loop, but a multi-file code repo selected from a Pareto frontier of genetically evolved candidates? RHO moves all its LLM exploration to training time, then runs that repo on scenes it was never trained on. 🧵👇🏽

显示更多