Thank you for the belly laugh!

This one made me laugh almost as much as the OP. Thank you!

Uuuhhhhh, copilot, is that you?!

Sure, long as you use your braing.

No, which is why I avoid regexes for most production code and also why I would never use one written by a pathological liar and always guessing coder like an LLM.

LLM is great when you’re coding in a pure fictional programming language like elm and are using loss of custom types to make impossible states unrepresentable, and the function you’re writing could have been derived by the Haskell compiler, so mathematically the only possible way you could write it wrong is to use the wrong constructor, then it’s usually right and when it’s wrong either it doesn’t compile or you can see it’s chosen the wrong path.

The rest of the time it will make shit up and when you challenge it, out will happily rewrite it for you, but there’s no particular reason why it wouldn’t make up more nonsense.

Regexes are far easier to write than to debug, which is exactly why they’re poison for a maintainable code base and a really bad use case for an LLM.

I also wouldn’t use an LLM for languages in which there are lots and lots of ways to go wrong. That’s exactly when you need an experienced developer, not someone who guesses based on what they read online and no understanding, never learning anything, because, my young padawan, that’s exactly what an LLM is, every day.

Watch your LLM like a hawk.

The experienced developers in the study believed they were 20% faster. There’s a chance you also measured your efficiency more subjectively than you think you did.

I suspect that unless you were considerably more rigorous in testing your efficiency than they were, you might just be in a time flies when you’re having fun kind of situation.

I was trying to think of some other meaning than ‘drinks dispensary’ for ‘bar’ and I couldn’t think of a sensible reason for putting a bar in your shower for quite a while until I realised metal bar.

On top of that, it’s an annoyingly disproportionate graphic. The cow is much wider than the human so its area is much more than 60% of the area of the graphic.

The owl might be 3cm high and the hen 6cm high, but 9cm² and 36cm² would be the rough areas, even if it weren’t for the fact that again, the hen picture is much, much wider than the owl.

With 30% and 70%, the owl should just be a little under half as big as the hen, but it looks like about 1/4 or 1/5 of the size of the hen.

Best comment on lemmy today.

That is stunningly beautiful. Wow.

It’s the physical grain of the canvas.

The fifth Doctor knows who the Portreeve of Castrovalva really is.

Yes and no. Beliefs can definitely shape reality.

If someone believes that they can’t do something difficult, they often don’t attempt it, so don’t acquire the skills they would need, and stay unable to do it. The converse is also true.

Children are heavily influenced by their parents’ beliefs about them.

Believing something about different brands of soda doesn’t change the chemical composition of them, but in a world where products are judged on their sales rather than their chemical composition, changing the perception of a product can fundamentally change its sales, making it a better product by the only objective measure that’s consistently used. This is even more true in the world of fashion, for example very strongly with trainers etc.

Anything where human behaviour changes reality is a place where beliefs change reality.

Our beliefs shape the world strongly and powerfully. They change reality.

Eg. USA.

(Personally and irrelevantly to your question, think it’s weird to shave your pubes, and I think that based on who started that trend, why they started it and why it became popular, but people younger than me, who don’t remember any different disagree strongly.)

But the fact that your son trusts you with that question and that you calmly helped him and didn’t make a big deal out of it, is an absolute parenting win. Who does your teenaged son go to when he’s worried about something personal and sensitive and embarrassing? He goes to you, and you help him and he is right to trust you.

You are doing excellently as a dad.

This graph is really, really wrong. Properly messed up.

This is you

https://youtu.be/mkcKQmr7kRc

I already told you my experience of the crapness of LLMs and even explained why I can’t share the prompt etc. You clearly weren’t listening or are incapable of taking in information.

There’s also all the testing done by the people talked about in the article we’re discussing which you’re also irrationally dismissing.

You have extreme confirmation bias.

Everything you hear that disagrees with your absurd faith in the accuracy of the extreme blagging of LLMs gets dismissed for any excuse you can come up with.

You’re so insightful and wise. You have learned much from other viewpoints.

It’s like you didn’t listen to anything I ever said, or you discounted everything I said as fiction, but everything your dear LLM said is gospel truth in your eyes. It’s utterly irrational. You have to be trolling me now.