I thought it was native. Click the three dots next to a result. I don’t have an extensions for it.

Light debugging I actually use an LLM for. Yes, I know, I know. But when you know it’s a syntax issue or something simple, but a quick skim through produces no results; AI be like, “Used a single quote instead of double quote on line 154, so it’s indirectly using a string instead of calling a value. Also, there’s a typo in the source name on line 93 because you spelled it like this everywhere else.”

By design, LLMs do be good for syntax, whether a natural language or a digital one.

Nothing worse than going through line by line, only to catch the obvious mistake on the third “Am I losing my sanity?!” run through.

30% do?

Fascinating…

Oh, I will. I’m getting along in years and am about to pick up split boarding for backcountry. I could learn to just ski, but I’ve lived life surfing and skating, so I picked up snowboarding real fast and been doing that a while now.

Kinda always been into the idea of towing with a snow mobile too, so maybe I can afford that around then haha

Don’t act your age. Get to a point where you’re so dismissive of your age you have to think hard about what your age actually is.

If I stopped and started doing things based on what I’m meant to do at an age, I’d be a miserable piece of shit. I just do and think what I want. When I’m 60, I’ll still be learning and doing what I want because I rejected the idea that I’m too old or too young for something.

Rather than setting sights on what you want to achieve, set sights on what you never want to become. The rest just flows around that and happiness is always there because you’ve identified what unhappiness is and stayed clear of it.

We can, but it’s a lot of effort and time. Good AI requires a lot of patience and specificity.

I’ve sort of accepted the gimmick of LLMs being a bit of a plateau in training. It has always been that we teach AI to learn, but currently the public has been exposed to what they perceive to be magic and that’s “good enough”. Like, being wrong so often due to bad information, bad interpretation of information, and bias within information is acceptable now, apparently. So teaching to learn isn’t a high mainstream priority compared to throwing in mass information instead—it’s far less exciting working on infrastructure.

But here’s the cool thing about AI, it’s pretty fucking easy to learn. If you have patience and creativity to put toward training, you can do what you want. Give it a crack! But always be working on refining it. I’m sure out there right now someone’s been inspired enough to do what you’re talking about and in a few years of tears and insane electricity bills, there’ll be a viable model.

Yeah, get too far in or give it too much to start with, it can’t handle it. You can see this with visual generators. “Where’s the lollypop in its hand? Try again… Okay now you forgot about the top hat.”

Have to treat them like simple interns that will do anything to please rather than admit the task is too complex or they’ve forgotten what they were meant to do.

I use Claude for SQL and PowerQuery whenever I brain fart.

There’s more usefulness in reading its explanation than its code, though. It’s like bouncing ideas back off someone except you’re the one that can actually code them. Never bother copying it’s code unless it’s a really basic request that’s quicker to type than to code.

Bad quality and mass quantity in is obviously much quicker for LLMs and people that don’t understand the tech behind AI don’t understand this actually what’s going on, so it’s “magic”. A GPT is fundamentally quite simple and produces simple results full of potential issues, combine that with poor training quality and “gross”. There’s minimal check iterations it can do and how would it even do them when it’s knowledge base is more bullshit than it is quality?

Truth is it will be years before AI can reliably code. Training for that requires building a large knowledge base of refined working solutions covering many scenarios, with explanation, to train off. It’d take longer for AI to self-learn these too without significant input from the trainer.

Right now you can prompt the same thing six times and hope it manages a valid solution in one. Or just code it yourself.

-ar is a person that does a thing. -er is a person that does action of a thing. A winkar in practice is a winker, but a winker isn’t necessarily a winkar.

But a winkee is definitely someone subjected to a wink, whether by a winkar or a just a normal person winking.

Yeah, but Paul kind of ruined Greece via Thessaloniki and Korinthos. Granted, the social hierarchy around the old gods backed by “the one true God for all” Christian narrative sure made it easy to turn common Greeks against their ancient culture and religion.

And they’ve been doing great ever since! cough, cough

Thanks to coding, I see center as a position and centre as an object. But for the most part, I find US spelling to be lazy spelling for poor pronunciation. Like people just started saying the word wrong and rather than fixing that, just started spelling it wrong too.

Aluminium is prob the weirdest. Like everything on the periodic table ending with -ium; the Latin morpheme in chemistry. But the US just-…like, how?!

No, no, no. This is all about race and not music genres. That’s why MTV is always playing Dean Martin instead of Louis Armstrong. /s

If white people want see more black people on MTV then they need to start liking the genres black people are currently doing. But why anyone would listen to music for a skin colour is fucking weird anyway.

What of any of that has to do with anything that’s been said by anyone? What the fuck are you smoking? Are you hallucinating words and trying to communicate back?

I just think they’re obsessed. Everything’s gotta be about Trump.

Probably hides a photo of him under their pillow for those moments no one’s looking.

When a cheap shot is so bad it doesn’t even have a connection.

“Some facts about Obama.”

“You must like Trump!”

You are so indoctrinated it’s pointless. Even hypotheticals are for realises at this level. Enjoy your society. You’ve made it what it is.

“Nah, eight words in, I think I’ve got enough here to unload my insecurities without it seeming at all irrelevant to the full comment. In fact, I’m so confident I have the full context, I’ll include a full-stop there in the quote. The words immediately after were probably useless. There! Now, time to finish it off with a ‘If you think…’ retort that will definitely be on point and worth everyone’s time.”

Wishing on a star?

“You don’t have to admit you were wrong”

🤣

What an opener to appeal for unity, Jesus fucking Christ.

The American Left and Right are indistinguishable people apart from political views.

Imagine what y’all could achieve if the circlerks were united as one big fucking circlejerk. That’s what Putin is blocking because GAWD DAMN was it effective in the last century.

But if unity can’t be started until someone admits something they don’t believe… Cool. Enjoy the dying years of your country, furled by stubbornness above all else.

I reiterate; The American Left and Right are indistinguishable people. Shouldn’t that mean something for common ground sake? Shake fucking hands ffs

Think select loose ideas of the Cultural Marxism conspiracy theory without the whacky details. The vibe of holding back progression by fueling division and tribalism, constantly asserting ones ideas and opinions over others without context to do so.

It makes the ideas and opinions less likely to happen because the people that say them do so without consideration of other’s opinions and ideas, imagining all individuals to be the same as the worst individual. This leads to the other tribe, who have the exact shortcomings as you and I, to mutually returns the same lack using the same terms and methods. Like “they”, “so you” and “tribe B wants to”. Not only does progression stagnate, it starts going backward.

MLK preached this heavily.

The lack of “because I want to understand” at the end of your comment implies your might be more poised to disregard or attack anything OP may have to say, rather than get a better understanding in effort to see how things can be mutually progressed. I hope I’m wrong in that.

And sorry for the bad typos. I cleaned what I could, but my screen is damaged.