How is program synthesis better than writing code?
the idea of program synthesis (like Rosetta) is to reduce a function into its constraints in a spec sheet, and generate the program from those constraints. for example, in order to write something like x = x squared, you would need to write a spec sheet along the lines of ∀x∈Z,f(x)=x2. i am considering building a program synthesizer, but I still haven’t figured out why exactly this representation is supposed to be easier than writing the code directly (they look equally complex) #technology