[progx]

And than you fix the produces shit, got high blood pressure and think "damn it,how I would love to yell at that employee"

[literalAardvark]

You say that, but it's been better than most employees for a year or so ( *for specific tasks, of course. It's still not better than "an employee" )

[josefrichter]

Not true at all with frontier models in last ~6 months or so. The frontier models today produce code better than 90% of junior to mid-level human developers.

[RealityVoid]

Just like a real employee!

[ben_w]

And just like a real employee, this makes it work worse.

(Old study, I wonder if it holds up on newer models? https://arxiv.org/pdf/2402.14531)