FaceDeer

Heh. I use Qwen3.8-27B as my main coding agent, and I sometimes feel really bad for it as I watch the stream of thought go by filled with “wait… am I doing this right? What if I’m completely wrong about this? Is this really what I should be doing??” I want to pet it and assure it that it should have more confidence in itself. :)

But it’s the tradeoff that Qwen made to cram that much smarts into such a small bundle of parameters, I guess.

If they pay you money then you can exchange that money for huge amounts of raw meat, if that’s what you really want. :)

Oh, I’m sure you wouldn’t love to look at it. :) It’s not exactly messy, AIs are good at keeping things tidy, but everything about it is ad-hoc. It was never intended to be seen my another mortal’s eyes than mine. I don’t think there are any API keys or other secrets tucked away in the repo’s history but I’d rather not risk it.

Your mess of files is different from my mess of files and the things you’d want to do with them is different from what my code does, I’d suggest getting your own agent on the task from a blank slate. That’s the whole point I’ve been arguing here, that coding agents make these kind of bespoke “home-cooked” applications a lot easier to spin up.

As I recall, my first steps weren’t even to have the coding agent write code. I explained my general goal and told it to look through the folders itself to see what work it thought needed doing. That was how I learned that almost all the cover art I’d downloaded from Udio years ago was actually AVIF format that had just been given the file extension JPG, for example - I didn’t even know that needed to be fixed.

Make sure you back up your files before turning an AI loose on them, of course. Mine’s been very well behaved (I warned it that avoiding data loss was the most important priority) but mistakes can be made.

Yes, AI generated. Use whatever word makes you happy, it really doesn’t matter to me. The key point is that it’s not music that would be on any existing catalogue anywhere. There’s no way to “look it up” anywhere. The only metadata that exists for those tracks are in the files on my own computer.

Oh by all means then. Free is free. :)

It is, in fact, all original work. Much of it has never been off the hard drive it was generated on (the stuff by local models), and when Riffusion got bought out they deleted all the stuff their users had generated so my local copies of those are the only ones left. The metadata is in sidecar .json files, except for the Udio tracks which were in .txt files that first needed to be converted to .json. All very ad-hoc stuff to begin with.

Also, it looks like Dropped Needle is aiming to make the music available for streaming through things like Jellyfin. That’s not what I wanted, I wanted to make a web site specifically so that I could control the layout and contents for when I share it with friends (many of whom are not technically savvy and so only know how to click on a web URL).

This really wasn’t a “just use pre-existing application X” situation. Even if there had been one that could handle all of that, configuring it would have taken just as much work as explaining to the coding AI what I wanted.

No I couldn’t’ve. I just had a look and that application has nothing to do with what I was doing.

All of the music in those folders was generated by me, some of it from a variety of different online services that are now defunct (Udio and Riffusion) and some of it from local music models. None of it is published anywhere, much of it’s never been off of my personal machine before. There was cover art for some of them in a variety of different formats. There were lyrics for most, but again in a variety of different formats - I had different metadata from each of the different sources and I wanted to unify them so they could be edited seamlessly. The lyrics were in .srt or .lrc format and usually needed hand-tweaking so I wanted a one-click way to open those in Subtitle Edit. I had a ComfyUI workflow that took descriptions, tags, and lyrics to auto-generate cover art for the songs, I wanted to be able to do that at the click of a button and hand-edit the image prompt if I didn’t like what it came up with. And so forth, lots and lots of special circumstances that applied to this bundle of data that are probably unique.

So I had a coding AI write tools specifically to handle all that. Super easy, barely an inconvenience.

I’d say “sure, why not?”

Depends on how expensive the tool is, mind you. I use local models so I’ve never had to poke around much at how much the paid ones go for, I don’t know what you’re using.

I know people who used to work there. It’s been dead inside for quite a while, and it wasn’t really EA that killed it. Bad management, mainly - they fought over turf and they constantly changed their minds about what sort of game was being made. There were basically two teams inside BioWare, the Dragon Age team and the Mass Effect team, and neither liked the other (at the management level that is - the coders and designers and testers down in the trenches were just their cannon fodder and got on fine).

After all the cuts the studio has suffered for the past few years, all the cannon fodder was already gone. The only people that were left inside that shell of a studio were the managers who had been fighting over it. The “winners” got to go down with the ship that they’d won.

I do think that the most dangerous point is probably past now, fortunately. The US would need to move a lot of assets around to make them ready for a full-scale attack on Cuba and I think we’re close enough to the midterms now that there isn’t time to get those in place before then. I could still see Trump launching some “decapitation strikes” between now and then though, maybe thinking he’d be doing the “Venezuela thing” and expecting the same results from that. Probably wouldn’t work but it’d still be painful.

No analogy is ever perfect, of course. That’s the point of an analogy, it’s not the actual thing.

In the case of vibe-coded apps, I think the thing that still matches up with “home cooked meal” is the fact that the app can be whatever you want it to be.

For example, I’ve got a big pile of music files I’ve accumulated over time from a couple of different sources with a couple of different styles of metadata, piled together in an ad-hoc assortment of folders. It’s an arrangement entirely unique to me. I had a coding AI create tools specifically to handle this pile, cleaning it up and organizing it, and had it build a website out of them that looked and behaved exactly how I wanted it to. It’s not the fanciest thing and the code could always use some refinement but it suits my needs perfectly. I’m not going to publish it because nobody else would find it useful, if they had a similar sort of situation to deal with they would be best served by having a coding AI whip up their own unique tool themselves.

The food analogy there is looking in your cupboard to see what ingredients you’ve got, thinking about what sort of food you’re in the mood for, and then throwing together something that fits those parameters.

This is what property taxes are supposed to be for. If a data center is putting a load on a community, tax them based on what money is needed to pay for what’s needed to counter that load.

Money is much more flexible than barter anyway. Imagine if instead of a data center it was an abbatoir, would you compensate the community for its troubles by giving them huge amounts of free raw meat?

If the kink you’re referring to is the amount of time Qwen’s “thinking” about your greeting, that’s not necessarily actually a problem. I’ve seen common misconceptions about exactly this kind of scenario.

Models like these are trained to follow instructions. When they receive a user input they think “what is the user asking me to do, and how do I go about doing it?”

If all you’ve said is “Hi”, that leaves them with a huge puzzle and no hints how to solve it. What does the user want them to do? Is this a test? Did they start writing an actual instruction and accidentally hit enter partway through? Do they want me to write a “hello world” app, and if so in what language? Is this the outout of a “hello world” app that I wrote in a previous round that I now need to check up on?

Qwen’s models are known to be rather “thinky” in the first place - it’s part of how they’re able to hit so high above their weight class - so it’s not surprising that it’s taking its time to figure out this challenge you’ve presented it with.

Sadly, it was already just a gutted shell of its former self at this point. This is just putting the zombie to rest.

And Trump’s term is only half finished.

It’s quite remarkable. Russia’s military proved itself to be an unexpected paper tiger when they launched an unprovoked attack on Ukraine, a completely unforced error. And now America’s done the exact same thing attacking Iran (though it’s still a bigger paper tiger than Russia’s military, so Cuba shouldn’t breathe a sigh of relief just yet). Trump longs to be like Putin, and a monkey’s finger curls on the paw…

Wait until you hear about a proposed new emergency method of keeping patients with respiratory failure oxygenated: enteral ventilation.

Some turtles do this naturally.

She is literally an example of someone who did get paid.

And then the BBC sues, wins, and eventually they just start seizing assets.

Trump has lost court cases and has paid out before.

There is demand, but that demand only exists because consumers aren’t being exposed to the actual price of AI.

I use AI extensively and it’s mostly via local models, which I pay 100% of the inference costs for.

If the only way this keeps going is propping up the industry with investor money and circular financing, then when one of those eventually give and the public are exposed to the true price of AI - what happens then?

Reduced AI usage. Not no AI usage, though. For example, my usage wouldn’t go down one whit. The price wouldn’t change at all for me.

The alternative was to not know how to fix it and bring it in to the shop for someone else to do.

How much do you use ChatGPT? Have you had much experience with its car repair suggestions recently?