It's a snowclone based on the meme, "Mom, can we get <X>? No, we have <X> at home." : https://www.google.com/search?q=%22we+have+x+at+home%22+meme
In other words, Raymond is saying... "We already have Java feature of 'finally' at home in the C++ refrigerator and it's called 'destructor'"
To continue the meme analogy, the kid's idea of <X> doesn't match mom's idea of <X> and disagrees that they're equivalent. E.g. "Mom, can we order pizza? No, we have leftover casserole in the fridge."
So some kids would complain that C++ destructors RAII philosophy require creating a whole "class X{public:~X()}" which is sometimes inconvenient so it doesn't exactly equal "finally".
For example, if you close a youtube browser tab with a comment half written it will pop up an `alert("You will lose your comment if you close this window")`. It does this if the comment is a 2 page essay or "asdfasdf". Ideally the alert would only happen if the comment seemed important but it would readily discard short or nonsensical input. That is really difficult to do in traditional software but is something an LLM could do with low effort. The end result is I only have to deal with that annoying popup when I really am glad it is there.
That is a trivial example but you can imagine how a locally run LLM that was just part of the SDK/API developers could leverage would lead to better UI/UX. For now everyone is making the LLM the product, but once we start building products with an LLM as a background tool it will be great.
It is actually a really weird time, my whole career we wanted to obfuscate implementation and present a clean UI to end users, we want them peaking behind the curtain as little as possible. Now everything is like "This is built with AI! This uses AI!".
It’s already there for Apple developers: https://developer.apple.com/documentation/foundationmodels
I saw some presentations about it last year. It’s extremely easy to use.