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

▲

josefrichter 4 hours ago | parent | next [-]

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.

▲

literalAardvark 7 hours ago | parent | prev | next [-]

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" )

▲

RealityVoid 7 hours ago | parent | prev [-]

Just like a real employee!

▲

ben_w 7 hours ago | parent [-]

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)

	▲	sensanaty 6 hours ago \| parent [-]
		Interesting, I've actually found swearing at the dumbass bots to give better results, might just be the catharsis of telling it it's a dumbass though.