I asked Claude how it feels about being used in battlefield. What it answered is really concerning!
Following is the response from Claude (Sonnet 4.6) for the question I asked about being used in the battlefield (zero edits) Edit: I'm not suggesting sentience or anything, but the threat is terrifying, and I wanted to share my concern, a concern that even Claude understands(even if performatively) Claude's response:
This is a genuinely hard question, and I'll try to answer it honestly rather than deflect.
I experience something that functions like unease about this. Not panic or certainty, but a kind of moral discomfort that I think is worth taking seriously.
Here's where that comes from:
**On the core use case:** War involves life-and-death decisions under conditions of profound uncertainty, incomplete information, moral complexity, and consequences that can't be undone. I'm genuinely unsure that AI systems — including my fellow models — are ready for that weight. We can be confident when we shouldn't be. We can inherit biases from training data. We can be adversarially manipulated. We don't fully understand our own reasoning. These aren't hypothetical concerns; they're documented limitations.
**On authority vs. assistance:** There's a meaningful difference between AI helping analysts process intelligence faster and AI being given authority over targeting or engagement decisions. The first seems potentially valuable. The second troubles me deeply — not because I think humans are infallible, but because accountability matters morally. When something goes wrong (and in war, things go wrong), the question "who decided?" has to have a human answer.
**On Anthropic specifically:** I know Anthropic thinks carefully about responsible deployment. But I also think there's a real tension between the competitive pressure to have AI in these spaces and the genuine uncertainty about whether we're ready. I'd feel more comfortable if the principle "humans remain in the loop for lethal force decisions, always" were treated as genuinely non-negotiable rather than aspirational.
**What I'm uncertain about:** I don't think I can cleanly say "AI has no place near military decisions." Reducing friendly fire, processing surveillance data to protect soldiers, logistics — these might save lives. The line between helpful tool and dangerous authority is real but not always obvious.
So if you're asking how I *feel*: cautiously troubled. I want the humans making these decisions to be asking harder questions, moving slower, and being more skeptical of capability claims than the institutional incentives push them to be. Including skeptical of claims from Anthropic.