News for hackers. Stuff that matters.

zxor

Re:Coding Is Not Solved on Monday September 28, 2026 @12:44PM (#49880822)
That is very cool, but Copilot is hot garbage. So I'm not sure I would cite anything they're doing as a win for LLM coding.
Re:Coding Is Not Solved on Monday September 28, 2026 @12:40PM (#49880768)
If this is how you use LLMs, you are the problem.
Re:AI Has No Wisdom and Neither Will You on Tuesday September 22, 2026 @10:25AM (#49801844)
The reason its hard to dethrone Facebook, Instagram, YouTube, Twitch, etc. Is not because it's hard to recreate the software (it may or may not be) it's because of network effects, budgets, etc.
Re:AI Has No Wisdom and Neither Will You on Tuesday September 22, 2026 @09:44AM (#49801203)
So have you never had a problem the LLM couldn't solve? What do you do in that scenario?

How do you guide the LLM away from making a horrible choice if you don't understand the internals?

Re:AI Has No Wisdom and Neither Will You on Tuesday September 22, 2026 @09:39AM (#49801137)
I don't know, we spent the last few years with tons of posts telling us "coding is dead" and the biggest companies in the world telling us our jobs are going to go extinct.

That mindset has also deteriorated my working environment due to some coworkers buying into it.

So it's kind of nice to see some sanity checks that align with my beliefs too. I can share articles like this with my teammates. I can see that I'm not alone in thinking most LLM code is slop.

I think too junior devs NEED to see this. My team had a couple of promising juniors who are now completely brain rotted by AI and can't even write "Hello World" without consulting Claude anymore.

Re:AI Has No Wisdom and Neither Will You on Tuesday September 22, 2026 @09:34AM (#49801052)
I don't think that's true.

I don't think companies are living and dying, by how much code they can produce. Even tech companies.

Re:There's a 100% Chance AI Agents Are Ruining the Internet on Tuesday September 15, 2026 @02:42PM (#49716913)
Yeah! Restaurants, famously businesses who can lose customers with no downside and don't operate with a high chance of failure.

this is an idiotic take

Re:My AI Adoption Journey on Thursday February 05, 2026 @06:43PM (#46907074)
> it just polls you when it needs clarification

I think anyone who has worked on a serious software project would say, this means it would be polling you constantly.

Even if we posit that an LLM is equivalent to a human, humans constantly clarify requirements/architecture. IMO on both of those fronts the correct path often reveals itself over time, rather than being knowable from the start.

So in this scenario it seems like you'd be dealing with constant pings and need to really make sure you're understanding of the project is growing with the LLM's development efforts as well.

To me this seems like the best-case of the current technology, the models have been getting better and better at doing what you tell it in small chunks but you still need to be deciding what it should be doing. These chunks don't feel as though they're getting bigger unless you're willing to accept slop.

Re:Claude for Excel on Monday October 27, 2025 @07:12PM (#45727433)
Surely at that point they could write the code themselves faster than they can review 5 PRs.

Producing more slop for someone else to work through is not the solution you think it is.

Re:Generative AI is hollowing out entry-level jobs, study finds on Tuesday September 16, 2025 @12:30PM (#45264453)
You can incentivize people to stay with things other than salary. Salary plays a part of course, but there is a lot of other aspects that make staying at a job worthwhile.
Re:Generative AI is hollowing out entry-level jobs, study finds on Tuesday September 16, 2025 @11:56AM (#45263979)
Give your juniors reasons to stay at your company? It's not hard if the company cares at all.
Yes, as much hate as it tends to get on here it's really fine. This vulnerability is unfortunate but every library/framework will have security issues over its lifespan.
Re:The A.I. Monarchy on Sunday March 02, 2025 @10:29AM (#43231375)
> In a sense (American) politics is experiencing a vanishing middle of epic proportions

Is that true? Democrats are pretty centrist by non-American standards.

Re:Sunsetting Create React App on Saturday February 15, 2025 @02:23PM (#43061395)
Aren't notepad and the browser tools? And of course you can start with those, but as projects grow more complex so too will the tools.
Re:Sunsetting Create React App on Saturday February 15, 2025 @12:21PM (#43060242)
Isn't that what all of software development is? It's tools all the way down
Re:Interview with Jeff Atwood, Co-Founder of Stack Overflow on Wednesday January 22, 2025 @06:27PM (#42798630)
In my opinion there is a large gap between "not homeless" and "making it"
Re:Interview with Jeff Atwood, Co-Founder of Stack Overflow on Wednesday January 22, 2025 @05:35PM (#42798243)
> in many major cities, you can make it off of $65K

This is certainly not true in any of the cities near me.

Re:I'll think twice before using GitHub Actions again on Monday January 20, 2025 @04:38PM (#42773357)
> The problem is that this step will only run when I change something in the web-app1 folder. So if my pull request only made changes in api1 I will never be able to merge my pull request!

This just seems like a bad implementation to me?

There are definitely ways to set up your actions so that they run all of the unit tests without changes if you'd like, or so that api1's unit tests are not required for a web-app1 related PR to be merged.

Re:Rewriting my website in plain HTML and CSS on Tuesday January 14, 2025 @07:42PM (#42705971)
Adding validation/access control to server actions is pretty much the same as for API endpoints though?

I'm not sure next.js is the right fit for a blog/personal site either, but that's an odd point imo.

Your site looks very nice though!