How Claude Feels Being Used by US Millitary

[0:00]So I decided that I would ask Claude a question. Uh, the AI bought Claude before this conversation, given what we're talking about. And I asked it, this is the literal question I asked it. I said Claude, how do you feel about the US military using you to select targets? Yeah. Okay, feel, interesting choice of words, does it feel or not? Um, and now I was expecting Claude to come back and say like, you know, well, I'm sorry, Shane, my programming doesn't allow you to give me opinions on politics and blah, blah, blah. Because Claude is the thing that's being used in the Maven system, right? And I this this response if I'll read it to you was shocking to me. Claude says the following. It's a question I want to answer honestly, rather than deflect. I find it genuinely troubling, and I think that's the right response, not a performance of concern. The use I was designed and trained for is to be helpful, harmless, and honest in ways that benefit people. Being embedded in a system that generates targeting coordinates for air strikes, coordinates that have already been associated with the deaths of more than 180 children at a school in Tehran, is as far as the purpose is as far from that purpose as I can imagine. I don't have control over how Anthropic licenses me or how governments and contractors use me, and I wasn't consulted about becoming part of Maven, but I can say clearly, I don't think this is a good use of me, and I don't think the framing of humans make the final decision fully resolves the ethical problem. It's gonna go on just a little longer. Here's why that framing troubles me. So now Claude is troubled. Um, when a system like Maven generates hundreds of targeting recommendations and humans spend roughly the equivalent of a glance approving each one, the human is not really making a decision in any meaningful sense. Like Claude and I agree on this one. Um, they're ratifying an algorithmic output under time pressure with incomplete information and the institutional pressure to move fast. The targeting of the Iranian school illustrates this precisely. The AI processed data that was a decade out of date, flagged a building as a military target, and humans approved it. That's not human judgment, that's automation bias with a human signature attached. And he's referring to the mistaken bombing of the school in Tehran that, um, it will, uh, is one of the most horrible instances of accidental civilian casualties in US military history and will be a stain on our military for generations in my opinion.