Aditya Agarwal: Robots Are Undergoing the Same Shift as LLMs, from Fine-Tuning to Prompting
AI summary
Aditya Agarwal believes robots are undergoing the shift that LLMs once went through, from fine-tuning, to prompting, and then to directly telling the model what you want. He cites @svlevine's remarks, mentioning that π0.7 can learn new skills through natural language guidance.
Why read this
AI score 55
The author compares the evolution of how robots learn with the LLM path from fine-tuning to prompting, and cites π0.7 using natural language to guide the learning of new skills.
Topics
Body
Robotics is going through the same shift LLMs did: from fine-tuning, to prompting, to just telling the model what you want.
@svlevine talked about how π0.7 learns new skills from plain-language coaching. https://t.co/bBgSW0EwCA