Mastodawn

And warnings like this should be the reason to ensure anything with AI has a physical switch to press. Unfortunately, we are instead putting AI into combat drones with lethal weapons.
#AI #warnings
https://www.marketwatch.com/story/will-ai-start-going-rogue-the-chorus-of-warnings-is-getting-louder-c4d4b831

We are far, far more likely to be intentionally harmed by human-directed AI than by a rogue AI, imo.

Which is to say, there are no rogue AIs, only ones trained that way.

@TheServitor the problem is, until you run into issues, you actually don't know if you trained the AI correctly.

hah. That's very true. I've only trained small models but it can be like catching a greased squirrel.