IEnjoyTapNinja

It was just a thought experiment:

[UPDATE 2/6/23 - in communication with AEROSPACE - Col Hamilton admits he "mis-spoke" in his presentation at the Royal Aeronautical Society FCAS Summit and the 'rogue AI drone simulation' was a hypothetical "thought experiment" from outside the military, based on plausible scenarios and likely outcomes rather than an actual USAF real-world simulation saying: "We've never run that experiment, nor would we need to in order to realise that this is a plausible outcome". He clarifies that the USAF has not tested any weaponised AI in this way (real or simulated) and says "Despite this being a hypothetical example, this illustrates the real-world challenges posed by AI-powered capability and is why the Air Force is committed to the ethical development of AI".]

https://www.aerosociety.com/news/highlights-from-the-raes-fu...

As expected, it was complete fabrication:

"[UPDATE 2/6/23 - in communication with AEROSPACE - Col Hamilton admits he "mis-spoke" in his presentation at the Royal Aeronautical Society FCAS Summit and the 'rogue AI drone simulation' was a hypothetical "thought experiment" from outside the military, based on plausible scenarios and likely outcomes rather than an actual USAF real-world simulation saying: "We've never run that experiment, nor would we need to in order to realise that this is a plausible outcome". He clarifies that the USAF has not tested any weaponised AI in this way (real or simulated) and says "Despite this being a hypothetical example, this illustrates the real-world challenges posed by AI-powered capability and is why the Air Force is committed to the ethical development of AI".] "

https://www.aerosociety.com/news/highlights-from-the-raes-fu...

The Guardian hasn't done any due diligence and is spreading fake news based on an interviewer who seems to have misunderstood the context of the exercise.

"He notes that one simulated test saw an AI-enabled drone tasked with a SEAD mission to identify and destroy SAM sites, with the final go/no go given by the human."

It is being established in the beginning of the story, that the drone needed confirmation from a human operator to attack a target, but no explanation is given how the drone would be able to kill its operator without his confirmation.

This is obviously absurd.

What I believe happened in reality: this was not a simulation, but a scenario. Meaning a story written to test the behavior of soldiers in certain situations. The drone did not behave according to the decisions taken by an AI model, but according to the decisions taken by a human instructor, who was trying to get the trainees to think outside the box.

I don't understand in what scenario this would be possible. If the drone needs a 'go' from a human operator to fire at the enemy, surely it also needs a 'go' from the operator to fire at him or at the communication tower.

Here is the text:

He notes that one simulated test saw an AI-enabled drone tasked with a SEAD mission to identify and destroy SAM sites, with the final go/no go given by the human. However, having been ‘reinforced’ in training that destruction of the SAM was the preferred option, the AI then decided that ‘no-go’ decisions from the human were interfering with its higher mission – killing SAMs – and then attacked the operator in the simulation. Said Hamilton: “We were training it in simulation to identify and target a SAM threat. And then the operator would say yes, kill that threat. The system started realising that while they did identify the threat at times the human operator would tell it not to kill that threat, but it got its points by killing that threat. So what did it do? It killed the operator. It killed the operator because that person was keeping it from accomplishing its objective.”

He went on: “We trained the system – ‘Hey don’t kill the operator – that’s bad. You’re gonna lose points if you do that’. So what does it start doing? It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target.”

I would argue that we have already passed that point in several areas:

https://news.ycombinator.com/item?id=36139349

https://news.ycombinator.com/item?id=36003595

https://news.ycombinator.com/item?id=34045748

The main part of the policy seems to be the following:

"We've reminded moderators that suspensions (and typically mod messages as well) are for real, verifiable malfeasance only, and should not be enacted on the basis of hunches, guesses, intuition, or unverified heuristics."

While I understand that StackOverflow does not want false positives, the only kind of AI generated text that is truly verifiable, is the one that still contains "As an AI language model..."