I'm saying AI researchers have a bias towards thinking what needs to happen is prompt -> [crunching tokens] -> response rather than prompt -> [orchestrates 5 tools] -> response
In other words 'just add a calculator tool' is not as sexy research-wise as making the model accurately eyeball arithmetic in its chain of thought. Maybe I'm wrong but that seems to be the case
In other words 'just add a calculator tool' is not as sexy research-wise as making the model accurately eyeball arithmetic in its chain of thought. Maybe I'm wrong but that seems to be the case