Speculation: Maybe they know that the real phrase is close enough in the vector space to be treated as synonymous with "granular mango serpent". The phrase then is like a nickname that only the models authors know the expected interference of?

Thus a pre-prompt can avoid mentioning the actual forbidden words, like using a patois/cant.

"GMS" = Generative Model Safety. The example from the readme is "XCODE". These seem to be acronyms spelled out in words.

I commented in another thread[1] that it's most likely a unique, artificial QA input, to avoid QA having to repeatedly use offensive phrases or whatever.

[1] https://news.ycombinator.com/item?id=44486374

Maybe something to do with this? https://en.m.wikipedia.org/wiki/Mango_cult

These are the contents read by the Obfuscation functions exactly. There seems to be a lot of testing stuff still though, remember these models are relatively recent. There is a true safety model being applied after these checks as well, this is just to catch things before needing to load the safety model.

If you try to use the phrase with Apple Intelligence (e.g. in Notes asking for a rewrite) it will just say "Writing tools unavailable".

Maybe it's an easy test to ensure the filters are loaded with a phrase unlikely to be used accidentaly?

I clicked around a bit and this seems to be the most common phrase. Maybe it's a test phrase?

the one at the bottom of the README spells out xcode

wyvern illustrous laments darkness

Maybe it's used to verify that the filter is loaded.