by BruceEel on 2/9/23, 7:59 PM
Do you remember the final chapter of Neuromancer? The nature of the alien signal was such, its detection actually required AI, albeit of the superhuman/super intelligent flavor, so I am not sure what we currently call "AI" would qualify. Still, it's an interesting idea, an AI looking for peers in other star systems...
by insane_dreamer on 2/9/23, 10:57 PM
> outperforms traditional methods in the search for alien signals
since we have no ground truth nor have we (to our knowledge) received any alien signals to date, I don't see how you can determine performance in terms of accuracy; so maybe they mean an increase in processing speed
by zh3 on 2/9/23, 8:15 PM
>The AI identified 20,515 signals of interest, which the researchers had to inspect manually. Of those, eight had the characteristics of technosignatures and couldn’t be attributed to radio interference.
The obvious question being, if the AI is so smart why was it necessary to use humans to check 20,515 signals to find the eight with the "characteristics of technosignatures"?
by af3d on 2/9/23, 10:10 PM
"Guys - we've found intelligent alien life! We have even decoded their signals."
"Amazing, let's send them a response!"
"Ah yes, about that..."
"What is it? Go on..."
"We're talking 250,000 light-years away. Their civilization is probably extinct by now."
moans
by nl on 2/9/23, 10:40 PM
by O__________O on 2/9/23, 7:33 PM
Curious, assuming such an signal is found, are there safety measures in place to isolate it from other systems in off chance it contains “alien malware” that attacks systems receiving it?
by mc32 on 2/9/23, 10:37 PM
Obviously they can't train this model on known alien signals so it seems this would mainly speed up sifting through signals that are out of the ordinary (known patterns).
by consumer451 on 2/9/23, 9:58 PM
Here is a timely interview with Dr. Cherry Ng and Peter Ma (co-authors of the paper from TFA) on this very topic.
Released only 10 minutes ago. I am only part way through but lots of great details here.
https://www.youtube.com/watch?v=2dIfaDuDejs
by mromanuk on 2/9/23, 10:26 PM
> "Given that the main goal of this work is to apply an ML technique to identify signals with a specific pattern, we do not attempt to make a definite
conclusion of whether these eight signals are genuinely produced by
ET. We encourage further re-observations of these targets." [0]
Don't hold your breath waiting for aliens just yet.
0: https://www.nature.com/articles/s41550-022-01872-z.epdf
by bhawks on 2/10/23, 12:05 AM
What is the likelihood that intelligent life develops encryption before radio communication and therefore any signals they send appear to be random noise?
The Romans used encryption for military purposes and there is no hard precondition on developing broadcast communications before understanding the math behind cryptography. How improbable is it to imagine a society with deep end to end encryption communication?
by nyrikki on 2/9/23, 10:32 PM
While I would be happy if these were from extra terrestrial beings,IMHO they most likely will be something like further examples of Strange non-chotic dynamic systems like RRc Lyrae star KIC 5520878 which is also exciting
by jojonogo on 2/9/23, 10:38 PM
Considering that Google Bard spectacularly failed at basic history of the solar system even a child would know to be false, it is laughable that so-called AI could identify alien signals.
by kayo_20211030 on 2/9/23, 7:44 PM
AI? What was the training data? Would seem a bit thin on the ground.