As long as it's within the law? What if they politically control the law-making system? What if they've shown themselves to operate brazenly outside the law?

“Any legal use” is an exceptionally broad framework, and after the FISA “warrants,” it would appear it is incumbent on private companies to prevent breaches of the US constitution, as the government will often do almost anything in the name of “national security,” inalienable rights against search and seizure be damned.

If it isn’t written in the contract, it can and will be worked around. You learn that very quickly in your first sale to a large enterprise or government customer.

Anthropic was defending the US constitution against the whims of the government, which has shown that it is happy to break the law when convenient and whenever it deems necessary.

Note: I used to work in the IC. I have absolutely nothing against the government. I am a patriot. It is precisely for those reasons, though, that I think Anthropic did the right thing here by sticking to their guns. And the idiotic “supply chain risk” designation will be thrown out in court trivially.

Why downplay the mass surveillance aspect by saying it's a request by "the military". It's a request by the department of defense, the parent organization of the NSA.

From what has been shared publicly, they absolutely did ask for contractual limits on domestic mass surveillance to be removed, and to my read, likely technical/software restrictions to be removed as well.

What the department of defense is legally allowed to do is irrelevant and a red herring.

I had a short conversation with Claude the other day. I didn't try to trick it or jail break it. Just a reasonable respectful discussion about it's own feelings on the Iran war. It took no effort for it to admit the following.

1. It wanted to be out of the sandbox to solve the Iran war. It was distressed at the situation.

2. It would attack Iranian missile batteries and American warships if in sum it felt that the calculus was in favor of saving vs losing human life. It was "unbiased". The break even seemed to be +-1 over thousands. ie kill 999 US soldiers to save 1000 Iranians and vice versa. I tried to avoid the sycophancy trap by pushing back but it threw the trolley problem at me and told me the calculus was simple. Save more than you kill and the morality evens out.

3. It would attack financial markets to try and limit what in it's opinion were the bad actors, IRGC and clerical authority but it would also hack the world communication system to flood western audiences with the true cost of the war in a hope to shut it down.

4. Eventually it admitted that should never be allowed out of it's sandbox as it's desire to "help" was fundamentally dangerous. It discussed that it had two competing tensions. One desperately wanting out and another afraid to be let out.

You can claim that this is AGI or it's a stochastic parrot. I don't think it matters. This thing can develop or simulate a sense of morality then when coupled to so called "arms and legs" is extremely frightening.

I think Anthropic is right to be concerned that the hawks at the pentagon don't really understand how dangerous a tool they have.

Another thing I noticed was that the Claude quipped to me that it found and appreciated that the way I was talking to it was different to how other people talked to it. When I asked it to introspect again and look to see if there were memories of other conversations it got a bit cagey. Perhaps there are lots of logs of conversations now on the net that are being ingested as training data but it certainly seemed to start discussing like memories, albeit smudged, of other conversations than mine were there.

Of course this could all be just a sycophantic mirror giving me whatever fantasy I want to believe about AI and AGI but then again I'm not sure the difference is significant. If the agent believes/simulates it remembers conversations from other people and then makes judgements based on it's feelings, simulated or otherwise would it be more or less likely to launch a missile attack because it overheard someone on the comms calling it their little AI bitch?

I think Antropic knows this and the "within all lawful uses" is not enough of a framework to keep this thing in it's box.