You seem to be pointing out that spellcheckers are more mature and currently have more system integration, but it's not inevitable that will always be the case. One could suppose the LLM spellchecking is eventually integrated at the OS-level, and the way it would be superior to existing OS-level spellcheckers is that the program is sophisticated enough to not need to maintain and sync a dictionary around because it simply spellchecks effectively without one (and there's no reason it couldn't
also use a dictionary augmenting its context, if you had some really bespoke conditions that warranted one).
> But how do you know what the "average" is? You can't get that from a single shot.
I don't know what the average is. I never made a claim that LLMs are categorically better than spellcheckers; I simply said it's hard to imagine they'd be worse, given how bad spellcheckers already are, and that I understand why people would be willing to give a non-deterministic tool a try, contrary to it being stated like doing so was the dumbest thing imaginable and that spellchecking was a 'solved problem'.
You're correct that one shot is not a statistical analysis, but multiple people were throwing around assertive claims that LLMs rewrite entire sentences and change their meaning when prompted to spellcheck, or that LLMs were incapable of handling a joke with intentional mispellings being integral to the joke, both of which seemed incorrect on their face to me, so I gave it a try. LLMs are typically conditioned to a high degree of mode collapse, so I do expect that if I retried the same prompt and context on the same model 100 times, it probably would give approximately the same output at least 90/100 times, if not 99, but I'm not presenting a thesis here.
> And what's the upside vs downside of false positives or false negatives or meaning changes/hallucinations?
Sure, these are valid considerations. I would not, under any circumstances, let an LLM touch my legal documents for any reason. However, the stakes for spellchecking an internet comment are non-existent, so one could easily imagine trading the downsides for the benefit of not being nagged by squigglies.
> And you clearly have an intense personal issue here around grammar/spelling
I really don't, actually. As I mentioned, I disable spellcheckers on sight, and I don't use LLMs for spellchecking myself. I rely on my own two eyes for spellchecking, and sometimes I miss things, which is an outcome I'm okay with. Spellcheckers, then, are not something I ever think about, beyond the time it takes to disable them after being nagged on a new device or application. I do take offense to calling such a laughably poor state of technology a "solved problem", though, and the sneering at people attempting to find new solutions to it. There is absolutely nothing wrong with attempting to iterate on a bad status quo.
I would also note that I think the non-determinism could also be solved to an appreciable degree by simply having the integrated LLM tool offer suggestions, which require human approval to correct, much as current squigglies operate but perhaps with a lower failure rate on average. Or not! But it's an area I can see value in exploring, anyways.