Code analysis firm sees no major benefits from AI dev tool when measuring key programming metrics, though others report incremental gains from coding copilots with emphasis on code review.
Is there anything it provided you so far that was better than the guidance from the Rust compiler errors themselves? Every error ends with “run this command for a tutorial on why this error happened and how to fix it” type of info. A lot of times the error will directly tell you how to fix it too.
I agree, although some messages are still cryptic for a newbie like me, but thats maybe more the person on the chair than the compiler 😇.
I’d estimate copilot to be correct in only 10% of the time, solving a situation like that. Most of the time the solution suggested is also wrong, but just differently.
Having said that: sometimes (small chance, 1% maybe) the solution is spot on.
AI mainly helps with the initial syntax and on language constructs and for that it is awesome.
Is there anything it provided you so far that was better than the guidance from the Rust compiler errors themselves? Every error ends with “run this command for a tutorial on why this error happened and how to fix it” type of info. A lot of times the error will directly tell you how to fix it too.
I agree, although some messages are still cryptic for a newbie like me, but thats maybe more the person on the chair than the compiler 😇.
I’d estimate copilot to be correct in only 10% of the time, solving a situation like that. Most of the time the solution suggested is also wrong, but just differently.
Having said that: sometimes (small chance, 1% maybe) the solution is spot on.
AI mainly helps with the initial syntax and on language constructs and for that it is awesome.