[jknutson]

I think they would want a more optimized regex. Like a long list of swears, merged down into one pattern separated by tunnel characters, and with all common prefixes / suffixes combined for each group. That takes more than just replacing one word. Something like the output of the list-to-tree rust crate.

[ahtihn]

Wouldn't the best approach for that be to write a program that takes a list of words and output an optimized regex?

I'm sure an LLM can help write such a program. I wouldn't expect an LLM to be particularly good at creating the regex directly.

[jknutson]

I would agree. That’s exactly what the example I gave (list-to-tree) does. LLMs are actually pretty OK at writing regexes, but for long word lists with prefix/suffix combinations they aren’t great I think. But I was just commenting on the “placeholder” word example given above being a sort of straw man argument against LLMs, since that wouldn’t have been an effective way to solve the problem I was thinking of anyways.

[solumunus]

Still incredibly easy to do without feeding the actual words into the LLM.

[nextaccountic]

But why are LLM censored? This is not a feature I asked for