Have you seen Boston Dynamics robot dogs? You think an LLM couldn’t be thrown in one and it just makes decisions on its own? Might not be exactly human but could be close enough to accomplish many tasks poorly for a while until one day it does them well and then we’ll really be living in a different world.
What exactly makes you say, LLMs are taking decisions? From what I understand it plays a probability game of predicting next set of words.
From those words chosen there is ReAct(Reason and Act) framework which selects the best possible next executable task from the choices provided to it.
For all I know, decisions are thought out actions using a logical flow and not predicting the next best token based on the previous token. And for every decision we are held accountable brute forcing our way to make decision is not viable IMO. Would like to hear other perspectives or would like to know if I missed something.
Have you seen Boston Dynamics robot dogs? You think an LLM couldn’t be thrown in one and it just makes decisions on its own? Might not be exactly human but could be close enough to accomplish many tasks poorly for a while until one day it does them well and then we’ll really be living in a different world.
What exactly makes you say, LLMs are taking decisions? From what I understand it plays a probability game of predicting next set of words.
From those words chosen there is ReAct(Reason and Act) framework which selects the best possible next executable task from the choices provided to it.
For all I know, decisions are thought out actions using a logical flow and not predicting the next best token based on the previous token. And for every decision we are held accountable brute forcing our way to make decision is not viable IMO. Would like to hear other perspectives or would like to know if I missed something.
https://www.ibm.com/think/topics/react-agent