BillionaireClubCollc
  • News
  • Notifications
  • Shop
  • Cart
  • Media
  • Advertise with Us
  • Profile
  • Groups
  • Games
  • My Story
  • Chat
  • Contact Us
home shop notifications more
Signin
  •  Profile
  •  Sign Out
Skip to content

Billionaire Club Co LLC

Believe It and You Will Achieve It

Primary Menu
  • Home
  • Politics
  • TSR
  • Anime
  • Michael Jordan vs.Lebron James
  • Crypto
  • Soccer
  • Dating
  • Airplanes
  • Forex
  • Tax
  • New Movies Coming Soon
  • Games
  • CRYPTO INSURANCE
  • Sport
  • MEMES
  • K-POP
  • AI
  • The Bahamas
  • Digital NoMad
  • Joke of the Day
  • RapVerse
  • Stocks
  • SPORTS BETTING
  • Glamour
  • Beauty
  • Travel
  • Celebrity Net Worth
  • TMZ
  • Lotto
  • COVD-19
  • Fitness
  • The Bible is REAL
  • OutDoor Activity
  • Lifestyle
  • Culture
  • Boxing
  • Food
  • LGBTQ
  • Poetry
  • Music
  • Misc
  • Open Source
  • NASA
  • Science
  • Natural & Holstict Med
  • Gardening
  • DYI
  • History
  • Art
  • Education
  • Pets
  • Aliens
  • Astrology
  • Farming and LiveStock
  • LAW
  • Fast & Furious
  • Fishing & Hunting
  • Health
  • Credit Repair
  • Grants
  • All things legal
  • Reality TV
  • Africa Today
  • China Today
  • "DUMB SHIT.."
  • Fast & Furious

“Superhuman” Go AIs still have trouble defending against these simple exploits

Enlarge / Man vs. machine in a sea of stones. (credit: Getty Images)

In the ancient Chinese game of Go, state-of-the-art artificial intelligence has generally been able to defeat the best human players since at least 2016. But in the last few years, researchers have discovered flaws in these top-level AI Go algorithms that give humans a fighting chance. By using unorthodox "cyclic" strategies—ones that even a beginning human player could detect and defeat—a crafty human can often exploit gaps in a top-level AI's strategy and fool the algorithm into a loss.
Researchers at MIT and FAR AI wanted to see if they could improve this "worst case" performance in otherwise "superhuman" AI Go algorithms, testing a trio of methods to harden the top-level KataGo algorithm's defenses against adversarial attacks. The results show that creating truly robust, unexploitable AIs may be difficult, even in areas as tightly controlled as board games.
Three failed strategies
In the pre-print paper "Can Go AIs be adversarially robust?", the researchers aim to create a Go AI that is truly "robust" against any and all attacks. That means an algorithm that can't be fooled into "game-losing blunders that a human would not commit" but also one that would require any competing AI algorithm to spend significant computing resources to defeat it. Ideally, a robust algorithm should also be able to overcome potential exploits by using additional computing resources when confronted with unfamiliar situations.Read 11 remaining paragraphs | Comments

Welcome to Billionaire Club Co LLC, your gateway to a brand-new social media experience! Sign up today and dive into over 10,000 fresh daily articles and videos curated just for your enjoyment. Enjoy the ad free experience, unlimited content interactions, and get that coveted blue check verification—all for just $1 a month!

Source link

Share
What's your thought on the article, write a comment
0 Comments
×

Sign In to perform this Activity

Sign in
×

Account Frozen

Your account is frozen. You can still view content but cannot interact with it.

Please go to your settings to update your account status.

Open Profile Settings

Ads

  • Billionaire128 Liquid Gold Yoga Shorts

    $ 30.50
  • Original Billionaire128 Basic Pillow

    $ 26.50
  • Original Billionaire128 Cuffed Beanie

    $ 19.50
  • News Social

    • Facebook
    • Twitter
    • Facebook
    • Twitter
    Copyright © 2024 Billionaire Club Co LLC. All rights reserved