I recently in $COMPANY had a coworker try fable to do a refactor where not breaking anything was the game.

It broke something at the first PR.

I think we’re not there yet.

I've found that adding "Make no mistakes." to my prompt usually helps with this kind of problem...

cubano an hour ago | parent | next [-]

perhaps simply threatening to fire it would also do the trick...it sure has worked well on us for a long time now.

lemming an hour ago | parent | prev | next [-]

Or if the code is really important, sometimes even “please make no mistakes” is necessary.

dozerly 2 hours ago | parent | prev [-]

We are so many layers deep in AI hype that I honestly can’t tell if this is /s or not

	▲	cadamsdotcom a few seconds ago \| parent [-]
		Plug it in to ChatGPT and ask for a summary and an opinion on whether it’s sarcasm, you’ll get something 10 times as long containing no information at all. Truly the future!