eatsyourtacos

Joined 4 years ago

Karma
906
Submissions
298
Member since
Jan 13
View on Hacker News

Recent submissions

Comment · 10 days ago
Fair enough but I can also tell you working with an LLM is basically a free second pair of eyes- even if you are the one writing the code.

Everyone who disagrees is just in pure denial or has never properly used an LLM to interact with regarding a code base.

Comment · 11 days ago
>"don't cry because it's over, smile because it happened"

Sorry but that doesn't apply to day to day work life...

Comment · 13 days ago
Same.. and now everything can be done SO FAST it's just stupid.

I used to love taking the time to whiteboard my project, write the code in peace (with maybe a background show). Go through the steps of structuring, debugging, testing.

Now I can write a prompt to basically do what I do instantly, and now I'm the manager and tester of something I didn't truly even make.

So sure the upside is I can do more, and I basically have to use it because I can't even keep up with what people want me to do without it. And it also seems so silly to go back.

Everything fun is just gone.

Comment · 18 days ago
Lots of people did.

And what did you do about it? Probably the same as the rest of us.. nothing that actually matters.

We have no power except a vote. Our country is too big (physically) to effectively protest. Our wealth distribution is too large. Our social safety nets are laughable. People can't even take time off work to protest, or if they just didn't show up they can be fired without recourse.

Our country and government is basically built for the people having no actual power. We are at the mercy of the ultra rich that control everything and a large majority of all of our "elected" officials.

Comment · 19 days ago
A human directing an LLM is often times no different than a human directing another human.

And the reality is you are setting yourself up for the most disappointing future you can imagine if your biggest concern is "failure to disclose LLM usage". Nearly everything you touch in every facet of your life going forward is going to have LLM usage to some degree. Some small, some very large. But you aren't going to be able to avoid it.

I'm not even advocating for anything -I'm just saying it's happening if we aren't there already.

Comment · 1 month ago
Check out Erenshor- I love playing with bots.
Comment · 1 month ago
Ok but you do realize that AI can also solve problems? The thing is it's not just taking away "the coding" it's also taking away the problem solving (of course I'm not talking about all problem solving).

That's the real risk here is that we are getting to the point (probably already there for a lot of stuff) where you can just point it to your already existing codebase and tell it your problem and it can basically do it.. I mean I've tested that in practice, sometimes I'll have a clear direction of where I want to go or what I would do.. but I don't really give it any hints of how to solve the problem, and many times it comes up with a similar result or at least one that also works completely fine.

So I think part of the issue is that people like you and me I feel like are going to be so much less needed because an AI can just do it instantly for basically free.

Anyway, I know this is a slight hyperbole.. but it's also not. It kind of sucks to realize that a simple prompt can replicate your work 95% of the time and do it basically instantly.

Comment · 1 month ago
>Vote with your money

That doesn't work in a society with such extreme wealth inequality.

Comment · 1 month ago
Good old PC video games are good at this as well. It's a joy to get into a game and not have anything else trying to pull you away with random crap.
Comment · 2 months ago
How about.. "it depends" ?

I review things that I know are "important".. but I've learned that there are many things that I don't care how it works at this point- they aren't critical in terms of I know it's not going to cascade and break other things (that's where us senior engineers know what to look for).

But there's no way in the hell I can review all the code that is being generated for so many things that just don't need reviewing. They work- that's honestly good enough for a lot of use cases. I review the code that touches sensitive areas and I know aren't very straightforward (which, I would put at only 10%).

Comment · 2 months ago
Well aren't you a ray of sunshine?
Comment · 2 months ago
The Sonic movies are really well done. The last two Mortal Kombat's were pretty good- particularly the second one which is more true to the game after the setup in the first one. The first Mario movie was enjoyable but forgettable.
Comment · 2 months ago
"Hey AI, find me a X cuisine restaurant around Y location that has availability at 7pm tonight" .. "Cool, book Z"

Seems obvious why an API would be helpful on that page instead of having the AI attempt to navigate the page, open up a date picker and click all around..

And as others have said, if you are disabled in some way being able to just speak and get something like this done seems pretty life changing.

But you go ahead and be mad about an api...

Comment · 2 months ago
The exact same can be said for human code... so what's your point?
Comment · 2 months ago
It doesn't matter if the LLM is not deterministic.. the OUTPUT of typed code is deterministic in the sense that it can be seen to be type safe, compiled, and run appropriate unit tests on it.

If I use two LLM's to create some chunk of code and they both do it slightly differently but they both compile and pass appropriate tests.. it honestly doesn't matter if the LLM itself is not deterministic in exactly what it's going to output.

I would also argue- doesn't that make sense? You give two human coders the same task and they are also going to come up with slightly different results.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton