Agreed, all of the staff/principal engineers I work with are ~99%+ AI generated code, and increasing business value delivered as a result. This is on planet scale infra not CRUD apps. (And yes, you do need to carefully review the output and give steers/corrections. It’s still faster.)

At this point if you can’t get the agent to write good code then either I) you are in a very specific niche (like Karpathy trying to write NanoGPT) that is extremely out-of-distribution, or II) skill issue, you need to learn how to prompt better.

It’s fine to have a skill gap! Just don’t delude yourself that the tools are bad and everyone claiming they are good is wrong.

▲

piker an hour ago | parent | next [-]

How is a GPT implementation “extremely out of distribution” but “planet scale infra” isn’t? That’s got me totally confused about your point that I was taking seriously.

▲

potatolicious an hour ago | parent [-]

A lot of stuff that underpins planet-scale infra is open source and has been for a long time. The general approaches and architectures for it have also been widely discussed and litigated in the commons so it's not just the code - the specific why is also very well documented.

So despite its importance much of it is actually pretty in-distribution.

	▲	piker 31 minutes ago \| parent [-]
		Okay, but then that does not square at all with calling a GPT implementation out-of-distribution, let alone "extremely" so.

▲

tripleee 30 minutes ago | parent | prev | next [-]

it's really cool how in the past measuring developer productivity was incredibly difficult, but now its become easy if someone's making a point about LLMs

▲

oasisaimlessly an hour ago | parent | prev [-]

btw, your last paragraph makes you sound like an ass.