HN user

wobblyasp

472 karma
Posts0
Comments114
View on HN
No posts found.

Verifying behavior is great and all if you can actually exhaustively test the behaviors of your system. If you can't, then not knowing what your code is actually doing is going to set you back when things do go belly up.

What an amazing place to run a business.

Absolutely no one is seriously clamoring for the old team name. It's an issue that DFM. But of course, because it's on the agenda of the day we need to drop everything.

This is no better then switch from master to mainline. They're both idiotic and performative.

I think the only thing that's going to change is expectation around deliverables.

I don't need an L4 to crack out some dirty code now, I'll let an agent do it so the L4 can level their skills up grinding harder problems.

I'm so fucking tired of people who had no interest in software development telling me software development is dead.

The author repeatedly states they have little knowledge of the tech they're using. But they're CERTAIN in what the industry will be in future.

Hubris

Again; made no comment about what people do day to day. Specifically commenting on the authors praise of the LLM doing "novel" work.

I sincerely doubt it; but I also work in an Org that has highly internal code with none to poor documentation.

Also, I never said it was a "downside". I'm simply stating that the author is exaggerating what the LLM is doing. It isn't creating novel code.

I used LLMs all the time to spit out boilerplate when it makes sense.

This wasn't something that existed, it wasn't regurgitating knowledge from Stackoverflow. It was inventing/creating something new.

Except it was. It wasn't regurgitating the exact answer it gave you, but it was using the collective knowledge of StackOverflow/other code to generate the solution.

Give your head a shake.

I'm confused.

Assistants are so easy to use yet we should drop everything to "learn"/"adopt" them? Why not just wait until they're not complete dumpster fires then start using them?

Reed Hastings' decision to pivot Netflix into original content production is a great example ... based on years of experience in entertainment and technology

Is it? How do you show that? Was he just lucky? Did he divine the right answer by listening to the voice in his head?

I don't disagree with the premise; when your body is screaming at you to do something that should feel unnatural you should be listening. That's evolution and learned experience trying to steer you away from danger or toward some kind of reward. But the blanket statement of "Stop analyzing your gut feelings" is just silly.

My gut tells me to do stupid shit all the time; if I didn't spend time thinking through the impacts of what may appear to be an "irrational" decision I'd expect to make many mistakes. This also gives leaders a complete scapegoat excuse when things explode (see WFH vs RTO, explosive hiring vs mass layoffs); hey, he was just following his gut, can't get it right every time.

I'd rather enforce it at the repo then hope and pray everyone updates their global configs.

Easy enough to catch but you'll miss some. Literally no cost to adding it to repo config either