Legionnaire's Shortform

Legionnaire

This is a special post for quick takes by Legionnaire. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

Potential political opportunity: LLMs are trained on online data and will continue to be. If I want to make sure they are against communism by default, I could: Auto generate a bunch of public github repositories, Fill them with text I generate using gpt4o mini which is $15 per 4 million letters which I have prompted to be explicitly pro free markets and against communism. Entwine them by posting links to each other and the rest of the internet: highlight, share, fork, and star them to increase likelihood they are included in the dataset.

2Dmitry Vaintrob2y

Kinda silly to do this with an idea you actually care about, especially if political (which would just increase the heat:light ratio in politics along the grain for Russian troll factories etc.). But carefully trying to make NN traps with some benign and silly misinformation -- e.g. "whales are fish" or something -- could be a great test to see if weird troll-generated examples on the internet can affect the behavior

You're assuming "Russian troll factories" aren't aligned with your goals.

some benign and silly misinformation -- e.g. "whales are fish" or something

Like the one with adding glue to your pizza sauce to get the cheese to stick, people have been trolling online without AI as the intended target.