8n4vidtmkvmk

Better get the trophy ready

I too built a terminal emulator and I like it, but I wouldn't say it's easy to maintain even with LLMs. The # of edge cases is insane.

Yes. It's fantastic for one-off tasks.

We're all just impressed that it's even possible. No one is saying these are fun.

I guess the next question is if they can be made fun without too much additional work with a human guiding the AI.

I think the difference is they're completable jobs. You work until it's done. At least for the day.

That word isn't any better. I am regardless of what I'm doing or how I'm feeling.

You want them to use .c++? Or .cpp?

Maybe they just want to use their country tld for things specific to their country instead of letting some shmucks scoop all the domains for useless junk?

Sounds ok but you know what else is Kubernetes for Rust? Kubernetes. Why use this, lighter weight? What if i also need to deploy non-Rust services across my cluster?

There's a reason they're not more popular...

90% of my over 250k rep is from asking questions.

Surely there's some value to asking a well worded question that many other people also have.

And yes, I've had my share of questions closed for some BS, including many in recent times closing 10 year old questions as dupes. Brilliant.

I was using the web app. Don't see any reason to use anything else for basic chat. Not having access to my computer is a feature

So why doesn't the US do it in reverse? Surely there's some R&D going on in China that US can reverse engineer.

That's the phone I was using too. Gave it to my wife a couple years ago and she used it until just a couple months ago when it too suffered a fatal drop. Very sad.

Good phone. I was worried about that pop up camera failing at some point, but it never did

I use flash 3.5 a lot. Its significantly worse than gpt 5.5.

Always was better IMO. I just pinned the browser app as a desktop app and have been using it that way for many months. Works great.

I don't know that we can have nice things. If two companies produce a similar widget but one is higher quality in no visible or articulable way... Which one will sell better, the cheaper or more expensive one? What if we as consumers can't really definitely tell when one is prone to failing in 1 year instead of 5? It takes too long to find out and by then the more expensive one is underselling and forced to enshittify.

I don't think it can give you story beats you shouldn't be aware of yet. Those beats wouldn't be fed into the prompt until the event happens. LLM can't spit out what it doesn't know.

It might indeed fail to reveal something it should but even that i think is unlikely if the harness steers it hard enough.

I think it could be fun. If you're always given 4 choices of what you can ask the NPC then your choices can be too obvious. If its open ended then you have to think a little what to say and ask.

I frequently steer the AI mid convo though. So much so that I find it useless to share the original prompt. I don't know how best to capture that.

We need like 3x the RAM to get the same value you were before.

How could Trump ban tiktok then? And Fable for that matter.

Maybe you're somehow legally allowed to distribute and download the weights, but most of us can't run GLM 5.2 at home.

Yes, absolutely. I use the largest interval any time I can get away with it!

Every Jan 2 I start saying "last year" and every Dec I say "see you next year"

What year is it? If you're running a barebones server, just use certbot. It'll automatically renew your certs. Very easy to set up and it's been stable for years without touching it.

New rule: when emailing someone, you need to include their name. If you do that, the email delivery gods will correct typos in your email address.

I thought the same for a long time but now i don't know. If your computer is compromised, they can exfiltrate your password, but with a hardware key they can't, so i think that's legitimately more secure than password+otp. It still needs a pin though to protect against device theft. I bring this up because there's been a ton of compromised developer packages recently and windows itself is being attacked so even if you're pretty good about protecting yourself, you still might get screwed.

ComfyUI embeds workflows in the EXIF data. It's very handy. Would be a little sad if they stripped that out but there are alternatives. I suppose if it's only cached images and not manually downloaded images it wouldn't be bad. It'd probably break some website somehow though.

The only reason I still read the output at my day job is because I still need to send it to another human for review, and I'd be embarrassed and ashamed if I let some slop through. For my hobby projects.. there are definitely parts I don't know how they work.

Maybe we need some form of long-term training. How long does the code that the AI wrote stick around before being rewritten.

I guess we can do this retroactively too if we could somehow tag AI-written lines of code in the VCS, then in a couple years we can check which parts lasted.

Might need some additional prompting? I haven't tried fable but gpt 5.5 and gemini 3.5 flash are... Ok on first pass but if you're specific about what you want they can usually get it.

Doesn't lock you out at all. Codex already had a companion app for mobile so you can send prompts to your desktop app while you go about your business. The infrastructure is there. Server might move from your desktop to cloud at some point but not much changes. Still needs somewhere to run.

Could be. I've been using most of the technologies you listed for over 20 years so none of that is really hard for me anymore.