So now we’re using AI to interpret “mysterious space signals”
While still being a bit on the frightening side, the science behind this story is still kind of cool and worth a look. The “mysterious space signals” referenced in the title are probably more familiar to those of you who follow such topics as Fast Radio Bursts (FRBs). They originate all over the universe, though not from our own Milky Way Galaxy (yet, thankfully), and are composed of compact, complex radio waves that don’t seem like the sort of thing you’d get from a normal spacial event like a supernova or the creation of a black hole.
The problem is, they are rare and very brief, so we’ve had trouble trying to track them and pin them down. Now a laboratory in Australia has worked out a way to use Artificial Intelligence to do just that. (NY Post)
Wael Farah, a doctoral student at Swinburne University of Technology in Melbourne, Australia, developed a machine-learning system that recognized the signatures of FRBs as they arrive.
Farah’s system trained the Molonglo telescope in Canberra to spot FRBs and switch over to its most detailed recording mode, producing the finest records of FRBs yet.
“It is fascinating to discover that a signal that traveled halfway through the universe,” he said. The research was recently published in the Monthly Notices of the Royal Astronomical Society.
Many of the intense flashes have traveled billions of light-years across space.
I recall watching a documentary on this phenomenon a while back and I’d thought they had determined that the FRBs were caused by supermassive objects like neutron stars that fall into a death spiral around each other and eventually collide. But the way these scientists are describing them, the FRBs apparently have “mysterious structures, patterns of peaks and valleys in radio waves that play out in just milliseconds.” This is unlike what you’d expect to see coming out of a massive collision or explosion like the ones that randomly happen around the universe.
So what are they? Signs of intelligent alien civilizations, as some have speculated? If so, they must be up to something pretty spectacular if it’s producing enough energy to reach us with that much power from far off galaxies.
But is this a good enough excuse to unleash even more Artificial Intelligence into the global web? I’ve sort of given up on hoping that we could avoid the eventual takeover of the robots once the AI wakes up and realizes that its creators are more of a nuisance than anything else and the first problem it needs to fix is… us. So if we’re going to be messing around with Artificial Intelligence anyway, I suppose we might as well let it listen for aliens.
That’s quite the pairing though, at least in terms of doomsday scenarios. Carl Sagan warned us long ago that alerting advanced extraterrestrial civilizations to our presence was probably a bad idea because it would wind up going poorly for us. And then there was Steven Hawking, who once said this on the subject:
“The real risk with AI isn’t malice but competence. A superintelligent AI will be extremely good at accomplishing its goals, and if those goals aren’t aligned with ours, we’re in trouble. You’re probably not an evil ant-hater who steps on ants out of malice, but if you’re in charge of a hydroelectric green energy project and there’s an anthill in the region to be flooded, too bad for the ants. Let’s not place humanity in the position of those ants.”
So now we’re mixing the search for possible extraterrestrials with Artificial Intelligence. As the old saying reminds us… what could possibly go wrong?
The post So now we’re using AI to interpret “mysterious space signals” appeared first on Hot Air.