HN user

bigstrat2003

9,053 karma
Posts0
Comments3,776
View on HN
No posts found.
Back to Kagi 10 hours ago

Yes, because I want actual answers, not something the LLM synthesizes which may or may not have any relation to the truth. LLMs suck for finding info if you care about the accuracy of the result (which I do).

That isn't a Jellyfin thing, Plex has the same issue. And both Jellyfin and Plex give you mechanisms to resolve that issue (using the alternate episode ordering that the metadata provider has, rather than the default one, or using another metadata provider if need be).

I can at least understand why someone watches a streamer, even though it isn't for me. Streamers tend to be charismatic and entertaining, so watching the person do his or her thing makes sense. But I can't understand the desire to watch a broadcast of a fake persona.

No, it isn't. It can autocomplete a fragment of a sketch of an idea into something that may or may not match the original vision and almost certainly has serious bugs which only manifest over time because they elude a cursory test.

quite a lot of software engineers would be very interested going though a similar journey now that LLMs removed most of the fun of programming.

I suspect we will see a reversal on this. LLMs are flat out worse than humans at programming (yes, even your latest favorite frontier model). I am faster (once you factor in the time fixing its inevitable mistakes) and better at programming than Claude is, and I'm not a particularly exceptional programmer. People say "they aren't going away", but I disagree with that - already we've seen people disenchanted with the lack of results compared to what they pay, and that is only going to grow once the AI companies raise prices in an attempt to turn a profit rather than lock people in. Eventually the industry will wake up and stop drinking the kool-aid, and what matters will once again be the results you deliver, not the tools by which you deliver them. But it's hard to say when that will happen, and it's going to be rough in the meantime.

No, we haven't. People do not "vote against their interests", as much as commenters online love to claim that. What actually happens is that they believe what they vote for will advance their well-being, and you disagree with their assessment. That's a very, very different thing.

The idea that there are any significant number of people out there deliberately hurting themselves for hate's sake is a complete myth. People reach for it because it feels good to imagine that your opponents are hate-warped idiots, but there is not a shred of evidence to support such a claim. When you actually talk to people (and not just assume you know what's in their heads), you find out that they, like you, are just trying to do good in an imperfect world.

To be honest, with how poor quality some software has gotten, I refuse to update it, security issues or no. Most products aren't that bad, thankfully, but there does reach a point where the theoretical risk of a security vulnerability is outweighed by the immediate issue of "this crap doesn't work any more".

When the blog post is under discussion, I think comments critical of it are just as fair game as ones which appreciate it. If the parent poster was emailing the author to make the same complaint then I think the "you don't have to read it" criticism applies, but not so much in a discussion forum. The point is to discuss what we think, even if that is a critical opinion.

Most people with experience in the tech industry would say that LLMs will make it worse. They make more mistakes than a human, faster than a human, but get treated (by management) as preferred to a human. The end result was never going to be more reliable software.

Anyone who lets the LLM put out unreviewed code is shockingly negligent and bad at his job. It certainly might be the case that many people are bad in such a way, but that doesn't make it acceptable.

I have seen no productivity uplift at all from LLMs. They are at least about neutral these days (they used to be a productivity drain), but no gains at all. By the time I get done reviewing the code to make sure it hasn't done anything crazy, I've spent the same amount of time I would've taken to write the code myself. The only people I personally know who claim productivity gains are getting those gains by completely disregarding quality, or understanding the code, and just YOLO letting the LLM do everything without checking. I'm not willing to do that.

Releasing software under permissive licenses is just wealth transfer from well meaning hackers straight into the pockets of corporations.

That is nonsense. A permissively licensed piece of software is every bit as free and a gift to the commons as a copyleft licensed piece of software. Yes, corporations get to use it, but so does everyone else. Free software was never about "fuck them corporations", it was about giving your work to others in order that all might benefit. Permissive licensing does that just fine.

If you're real question is what can be done better by hand in July 2026?

The answer to that question is "everything". Humans are still noticeably better than LLMs at writing code, and just as fast once you factor in the time it takes to review and correct the LLM.

Outside of work (where they force me to use the clanker), why on God's green earth wouldn't I write code by hand? That is the fun part; I'm not going to voluntarily give up the fun part of my hobby project. If you are a person who is wired to care more about getting to the end than the process (as some here have said they are), then fine, use an LLM if you want. But there's no "makes sense to" involved here - if you like writing code then write code, if you don't then don't.

I hate LLMs so, so much. They are destroying everything that used to be cool about programming. Or maybe the problem is that a bunch of people who don't actually like programming joined the industry, and now they have a tool that lets them phone it in even harder.