Appendix

I wish people would find a decent source for these stories in order to post them on here instead of sending us to a tweet. I'm not on Twitterx and it's a mini nightmare on a mobile browser

Contrary to popular belief, twitter/x is completely fine.

My dad always used to say I was addicted to screens growing up. I don't think he was far off the mark (nowadays he's as bad as me)

One time, almost all of my hobbies involved computers. I was a coder. A gamer. A writer. A digital artist. A filmmaker. I made fun Photoshop things for friends. I built websites. I did a lot of dtp. I made music with music apps. All of these things involved me staring at a screen for hours, but I don't consider them wasted time.

As I've gotten older and had kids I've tried to dial it down. I don't game anymore. I don't do social media. If I draw, it's usually with the kids on a giant sheet of paper on the floor. I spend a lot of time with my kids and it makes me happy. But even in that, I would have to concede I spend far more of my day and week in front of a screen than talking to humans.

One of the most common regrets on the death bed is "I wish I hadn't worked so hard, I wish I'd spend more time with my family", And while I don't have the benefit of 7 decades of hindsight and any clarity of mind that comes with being near death, it does seem to me like a slightly unrealistic idea, that we simply could have chosen to work fewer hours and spend more time with loved ones.

Most of us work 40 hours a week to pay the bills, and most of us can't afford to cut down that time. And I would guess for most of the people on hn, those 40 hours are spent in front of the computer.

We all have to work, and we can't all just wave a magic wand and step away from the computer and spend time with the kids instead. Otherwise said kids will end up without a roof over their head.

Yes, you probably spend more time in front of a computer than you do talking to your children, but don't beat yourself up about it

> One of the most common regrets on the death bed is "I wish I hadn't worked so hard, I wish I'd spend more time with my family"

You are not the same person as the one on your death bed. You do not have the same priorities. The only thing left for the person on the death bed are memories, so it's natural that this is a common regret.

It's a bit of a trap, kids are so expensive, if you dont have kids working an easier job is completely viable, but obviously you dont have the kids to spend time with, if you do have kids you need to work flat out to support them. I dont think myself and my partner will be having children, and there's a myriad of reasons for that, but the economic implications are certainly up there.

Kids are expensive, no doubt. But if you want kids, don't let money be the thing that stops you. That would be a far bigger regret

Total sidebar, but mun logadans site is better than browsers readability modes. I find it so easy on the eye even though the text is tiny on my phone. I don't know what font css combo is being used but it's perfect

There's a better solution and that is to just not go on Facebook

The last time I went on Facebook, the ads were so similar to posts it was near impossible to tell one from the other. The problem is compounded by elderly relatives liking or sharing weird AI posts, and an algorithm that seems to be random and non deterministic

There's some variety of little people myth in most cultures. There's also giant myths in most and there's no mushroom for that.

I think those kinds of myths are just natural progressions of exaggerations and oral storytelling

If anyone is triggered by AI content they surely avoid HN

I love AI content. I hate content written by AI.

It's not serious. It shows that the author doesn't care about showing what he's up to.

He cares about making content to post on a blog.

And that's disrespectful to the reader.

I'm not an editorialist, I spend my time on the software side of things, but want a detailed technical journal of what happened to achieve the gains. Also why the github link is near the top of the intro which I wrote. I'm not trying to disrespect the reader, but the time of the user of the software. Appreciate your view. I've made adjustments.

I spend all day reading AI generated text in one form or other in my day job. When I come to unwind in HN I’m not interested of more of the same. Seeing “load-bearing”, “landing things”, “it’s not x, it’s y” makes me think of work. I honestly would rather read human text with typos and warts.

Load bearing is a funny one because before LLMs the only time I heard it was in the phrase 'load-bearing bug'.

It got a lot of use in comedy screenwriting. How many shows have you seen where someone says "don't touch that, that's a load-bearing [object that should never be load bearing]"

The fort episode of community springs to mind but there are plenty others

And my point is you'll find both on HN

> But so far most of what they do is make more annoying work for me. More integrations to debug, more auth tokens to refresh, more bills to keep track of, more meandering and drawn out descriptions of non-bugs with bogus fix suggestions and misinformed “root cause” analyses. It’s tiresome.

God this times 1000. I'm so sick of having AI chase a bug and having to lead it by the hand like a toddler to try and help me solve bugs. The difference is, a toddler learns when you explain. An LLM holds your responses in context and uses them to generate more authentic sounding garbage, but next session, foomf, the lesson is unlearned again.

I had a tiny problem with prerendering not working on a react site last night, I must have spent close to an hour running commands it asked me to run like a moron, verifying dumb things I had already checked like "did the file actually upload to ftp" or had I restarted Apache or was there some magic htaccess file somewhere. Eventually I just gave up on Claude and tried some different paths in Apache virtual host settings and it worked.

Of course if I went back to Claude and reported that, as would be my instinct with a human, it would confidently explain why that was the bug, why it couldn't spot the issue, and how smart I am for finding it. And then it would forget everything tomorrow

I suspect the issue there was Claude, especially Opus 5, which just hates the idea that it could ever be wrong about anything.

> I'm so sick of having AI chase a bug and having to lead it by the hand like a toddler to try and help me solve bugs.

This hasn't been my experience at all. I can give it a vague description of the problem and have it find it pretty easily without any more input from me.

I do think there's a pretty big variation in tools and setups and what output people are getting. I'm now just using OpenAI Codex in VS Code and it churns through problems like they're nothing.

Sometimes I have to get it to not over-engineer a solution; not because it's necessarily wrong but because I don't need that much correctness.

Oh I'm not saying it happens every time, but maybe one in twenty, you'll get a problem that sends it in circles, and that's enough

> Cyan hoped it would come away from the conferences with a funding agreement between $1 million and $10 million to finish building Anglerfish.

This seems like an insane amount of capital to make a game that could be vibe coded in a few weeks