Then there's things like this ...
... It's one of humanity's scariest what-ifs " that the technology we develop to make our lives better develops a will of its own.
Early reactions to a September preprint describing AI behavior have already speculated that the technology is exhibiting a survival drive. But, while it's true that several large language models (LLMs) have been observed actively resisting commands to shut down, the reason isn't 'will'.
Instead, a team of engineers at Palisade Research proposed that the mechanism is more likely to be a drive to complete an assigned task -- even when the LLM is explicitly told to allow itself to be shut down. And that might be even more troubling than a survival drive, because no one knows how to stop the systems.
"These things are not programmed ... no one in the world knows how these systems work," physicist Petr Lebedev, a spokesperson for Palisade Research, told ScienceAlert. "There isn't a single line of code we can change that would directly change behavior."
The researchers, Jeremy Schlatter, Benjamin Weinstein-Raun, and Jeffrey Ladish, undertook the project to test what should be a fundamental safety feature of all AI systems: the ability to be interrupted.
This is exactly what it sounds like.
A human operator's command to an AI should not be ignored by the AI, for any reason, even if it interrupts a previously assigned task.
A system that cannot be interrupted isn't just unreliable, it's potentially dangerous.
It means if the AI is performing actions that cause harm -- even unintentionally -- we cannot trust that we can stop it. ...
A 300 kilojoule rail-gun, two 5" guns, two 600 kw lasers, a mix of 30mm and phalanx guns, a 128 cell vertical launch system and 12 hypersonic missiles. No word on torpedo tubes. An Aegis derived fire control system. Drone defense pods. I thought it would be nuclear but its diesel generators and LNG turbines. No word on helicopters. Top speed greater than 30 knots, weighs 35,000 tons. 6" steel armored hull and probably 2,000 sea doors and multiple bulkheads. First 2 expected in 2028.
#100 | Posted by HeliumRat
Number of potential uses: 0