This is a great example - it kinda makes sense if you skim read it but butterflies have nothing to do with butter, just like hotdogs have nothing to do with dogs.

FiveSixEleven downvotes and counting…

LLMs are already being used for policy making, business decisions, software creation and the like. The issue is bigger than summarisers, and “hallucinations” are a real problem when they lead to real decisions and real consequences.

If you can’t imagine why this is bad, maybe read some Kafka or watch some Black Mirror.

My friends would probably say something like “I’ve never heard that one, but I guess it means something like …”

The problem is, these LLMs don’t give any indication when they’re making stuff up versus when repeating an incontrovertible truth. Lots of people don’t understand the limitations of things like Google’s AI summary* so they will trust these false answers. Harmless here, but often not.

* I’m not counting the little disclaimer because we’ve been taught to ignore smallprint from being faced with so much of it

I found that trying “some-nonsense-phrase meaning” won’t always trigger the idiom interpretation, but you can often change it to something more saying-like.

I also found that trying in incognito mode had better results, so perhaps it’s also affected by your settings. Maybe it’s regional as well, or based on your search result. And, as AI’s non-deterministic, you can’t expect it to always work.

I had “install Linkwarden” on my todo list; Hoarder/Karakeep seems very similar, does anyone have opinions on which is better?

Not your post, either ;) We’re c/selfhosted around these parts.

I think it’s more that using tho instead of though is quite casual, but then you use thusly, which is rather formal. The change of register is surprising/funny.

Like if someone wrote “Indeed, it is most unexpected lol”.