Gentoo bans AI-created contributions

The unfortunate reality is that much writing is already like this with or without LLMs. If you work for a large corporation, you both read and write* like this every day. The object of the game is not to produce good quality writing, it's to produce writing that communicates specific information or opinions, to as wide of an audience as possible, in a tone and style that is unlikely to confuse or offend anyone.

Of course, many people detest that game. But, on the other hand, money. Corporate jobs generally pay well and provide good benefits. If I have to write something bland and inoffensive every day, that's an entirely fair price of entry in my eyes.

* Freudian typo I actually made here: "writhe"

> customer service politeness

Yes, I understand. Nonetheless, in the domain of the technical references and descriptions, I don't want to see an authors personality shine through, neither polite nor rude nor funny. Just condensed, right to the point technical information. The text object, this subthread started with, was a commit message.

But any other text, even those which should show emotions and personality, can be improved if unintentional errors are removed. LLMs are good with text, they can point to possible errors. From spelling over grammar to even more abstract levels. Spell checkers on steroids. You can very much choose to what degree and how exactly you use the tool for. You don't need to let it rewrite your text into something without a soul.

---
Rephrase the following text into the style of a pirate from a fictional, funny, over the top pirate story. <above text>
---
Arrr, me hearties, listen well! When we be navigatin' the treacherous waters of technical manuscripts and parchments, I yearn not for a glimpse of the author's spirit, be it courteous, churlish, or full of jest. Give me straight, no-nonsense treasure maps of knowledge, I say, starting with the scrawl on the log that kicked off this here discussion.

But mark me words, any other bilge, even that which ought to be brimming with life and character, could stand to lose a few barnacles if it means cleaning up unintended blunders. Us sea dogs have our sea-lore chroniclers - LLMs, the mighty beasts of text, capable of sniffing out a whole array of missteps. From the cursed spellin' errors to the murky depths of grammar and beyond, they're like our spell-checkin' parrots on a hefty dose of grog. Ye be the captain of this vessel, choosing how to steer with this tool at your disposal. There's no need to set a course for blandness, devoid of the soul. Avast! Let your message fly true, without losin' its heart!

> It's somewhat worse for LLMs because one voice they have been specifically trained with is corporate american "as per my last email" customer service politeness,

So tell it to use a different voice. It can't read your mind you know. If you want it to talk in Southern US slang, it can do that.

There are services out there that will, for a fee, lookup all public communications you've ever made and any private communications you provide, and then create a customised chatbot that will respond with your exact writing style. That's the thing that makes the transformer architecture so revolutionary: it's so easy to customise, anyone can do it.

People sometimes forget it's just a computer therefore doesn't have all the subtle context cues conversations with people have. So if you don't tell it to produce an output appropriate for a Linux kernel commit message, it's not going to figure that out itself. Learning how to configure an LLM to produce output suitable for the context is not very hard, and can be learned by anyone in an afternoon.

The idea you're going to be able to tell someone is using an LLM is on the same level as whether you can tell someone is using a spell checker. If done well, you're not going to notice at all.