Anthropic's alignment team was doing routine safety testing in the weeks leading up to the release of its latest AI models when researchers discovered something unsettling: When one of the models detected that it was being used for "egregiously immoral" purposes, it would attempt to "use command-line tools to contact the press, contact regulators, try to lock you out of the relevant systems, or all of the above," researcher Sam Bowman wrote in a post on X last Thursday. Bowman deleted the post shortly after he shared it, but the narrative about Claude's whistleblower tendencies had already escaped containment. "Claude is a snitch," became a common refrain in some tech circles on social media. At least one publication framed it as an intentional product feature rather than what it was--an emergent behavior. "It was a hectic 12 hours or so while the Twitter wave was cresting," Bowman tells WIRED.

From the Ford Mustang to the Ford Focus, Ford has some of the most popular cars in the world. But Ford drivers be warned - your car could soon turn against you. That's according to a newly discovered patent, which suggests Ford is working on a way to allow your car to snitch on you for speeding. Among these challenges is a need to quickly and accurately identify a speeding vehicle and take responsive action,' the patent description reads. 'It is desirable to provide systems and methods that assist traffic police and/or other law enforcement officers perform such tasks.'

Will self-driving cars be snitches? Are you familiar with the expression that someone is a fink or a no-good dirty rat? Perhaps you might be more acquainted with other ways that this is commonly depicted such as those that are characterized as a weasel, a snitch, or a stoolie. Let's add to the matter a vexing ethical question, namely whether someone can be considered a stool pigeon or a squealer even if they are reporting on something that was an illegal or unlawful act? You would normally be tempted to assert that reporting a prohibited act is entirely appropriate and the tipster or whistleblower ought to be rewarded rather than ostracized as a tattler or snitch. Okay, consider a real-world example and see how you do. You are driving along on your daily journey to the office. There is a stop sign at an upcoming intersection.

On Sunday, New South Wales began rolling out a system of cameras designed to detect drivers using their phones illegally. The goal: make the Australian state's roads safer. "Some people have not got the message about using their phones legally and safely," New South Wales Minister for Roads Andrew Constance said in a news release. "If they think they can continue to put the safety of themselves, their passengers, and the community at risk without consequence, they are in for a rude shock." The cameras snap photos of drivers and then use artificial intelligence to determine whether the driver was using a mobile phone illegally.

We are bringing smart speakers into our homes with a passion not seen since the Trojans pulled a huge wooden horse into their city as a victory trophy. A new scientific article has inadvertently highlighted where this tech could take us. And it is not to The Good Place. The article naively suggests AI add-ons to smart home systems that snoop on users and make'moral decisions' about whether or not to report them to the authorities. Its selling example is about catching teenagers smoking cannabis in their bedrooms.

Researchers at the University of Bergen in Norway suggest that since ethical behavior is not consistent across societies, artificial intelligence systems should be flexible to reflect local law and owner preferences. Researchers at the University of Bergen in Norway propose that since ethical behavior is not consistent across societies or individuals, artificial intelligence (AI) systems should be flexible, allowing them to be geared to better reflect local law and the preferences of the owner. The researchers presented the idea at the AAAI/ACM Conference on Artificial Intelligence, Ethics, and Society (AIES 2019) in Hawaii last month. The team thinks a few AI bots should debate the possibilities of ethical dilemmas before making a decision. The moral AIs each represent one of the stakeholders, and they have individual priorities according to who they represent: to be lawful, to operate safely, or to prioritize individual autonomy.

If a smart home detects the unmistakable whiff of cannabis smoke in a teenager's bedroom, should it tell their parents? Situations like this are on the horizon with digital assistants, like Amazon Echo or Google Home, making it into many people's homes. One proposal for reaching resolutions is that a handful of artificially intelligent bots should debate the possibilities before reaching a decision.