Well I kept using it until Infinity died, which was only at the start of this month!

If I do decide to go back, it will be by compiling the infinity APK with my own API key, but I’m not feeling much of an urge to bother at the moment.

I think calling it just like a database of likely responses is too much of a simplification and downplays what it is capable of.

I also don’t really see why the way it works is relevant to it being “smart” or not. It depends how you define “smart”, but I don’t see any proof of the assumptions people seem to make about the limitations of what an LLM could be capable of (with a larger model, better dataset, better training, etc).

I’m definitely not saying I can tell what LLMs could be capable of, but I think saying “people think ChatGPT is smart but it actually isn’t because <simplification of what an LLM is>” is missing a vital step to make it a valid logical argument.

The argument is relying on incorrect intuition people have. Before seeing ChatGPT I reckon if you’d told people how an LLM worked they wouldn’t have expected it to be able to do things it can do (for example if you ask it to write a rhyming poem about a niche subject it wouldn’t have a comparable poem about in its dataset).

A better argument would be to pick something that LLMs can’t currently do that it should be able to do if it’s “smart”, and explain the inherent limitation of an LLM which prevents it from doing that. This isn’t something I’ve really seen, I guess because it’s not easy to do. The closest I’ve seen is an explanation of why LLMs are bad at e.g. maths (like adding large numbers), but I’ve still not seen anything to convince me that this is an inherent limitation of LLMs.

Thanks for the info on crossposting! I thought I’d seen someone mention a cross posting feature but couldn’t see any button to do it. I’m using the Jerboa app on Android which I guess doesn’t have that button, but I see it on the website now as you say.

It’s also good to know that linking to the original URL is generally better and the rest can be handled by the UI - that does seem nicer.

I’d be happy if we’d just accepted “referer” as the correct spelling for everything, but instead we have the “Referrer-Policy” header, so now I need to check the correct spelling for anything involving referring…

I do sort of like the idea that because we want to keep backwards compatibility on software we just change the language instead since that’s easier.

Is “scrapping” autocorrect, a typo, or intended? Not meaning to be rude just interested because I’ve only heard of “web scraping” but often see people write “scrapping”.

Google yeah, but I don’t think YouTube is too much of a stretch, especially now they have posts and polls and other stuff.

Lemmy still feels pretty niche so I also found it surprising for me, although it probably shouldn’t be, there are quite a lot and they have to be somewhere :)

My understanding (from limited knowledge) is that also due to how federation works even if you’re instance isn’t under too much load, you may notice issues with posts/comments from other instances if they’re struggling.

Agreed, and the questions I have that MDN doesn’t answer would probably be ones even less likely for the AI explain to get right.

Confusable characters get a little yellow box which is different from the squiggly underlines most linters and stuff use which at least makes it a bit more recogniseable.

Personally I can’t stand having underlines all over my code, so I’ll usually just “fix” the non-issue if possible, or otherwise just disable whatever the warning is entirely.

To be fair, it’s no worse than articles some people write on those nonsense websites.