Homepage / Technology / An artificial intelligence lab founded by Elon Musk is trying to prevent machines from going rogue
Menyelami Dunia Slot Thailand: Keseruan dan Peluang Kemenangan Besar Menyelami Dunia Slot Thailand: Pengalaman Bermain yang Tak Terlupakan เว็บพนัน ออนไลน์ จับกลางกรุง! บุกทลายฐานเว็บพนันชาวไต้หวันรายใหญ่ เงินหมุนเวียน 500 ล้าน ปี Panduan Lengkap Bermain Slot Online: Strategi & Tips Terbaik Deneme Bonusu ile Ücretsiz Oyun Oynayın Boy Names: Top 1,000 Baby Boy Names in the U S. for 2024 List of most popular given names Wikipedia Mobile Gaming in the UK: Trends, Regulations, and Future Leads Start dating hot moms today – it’s easier than you think Define generative ai 14 Define generative ai 14 How to find the right online gay dating website for you Home Superclones watches Exploring Super Clone Watches: Quality, Accuracy, and Affordability Join the most effective bbw milf dating site today En İyi Bahis Siteleri İçin Seçim Yaparken Nelere Dikkat Edilmeli? At this point, and yet very near | Life and magnificence | Trusted Casino Hellspin Review Leading Online Casino Hellspin Evaluation Mostbet App: Download Mostbet apk for Android & iOS 2024 Ігрові Автомати з Виводом Грошей на Карту ️ Онлайн Ігри на Гривні в Українікращі азартні ігри на гроші з виводом на карту2024-01-08 Taya365 online casino login Tips for conference and dating other bisexual men How to get the right bi partner Exploring the Prospering World of Online Casinos in the UK Meet hot singles and luxuriate in flirty chatting Bahis Siteleri: En İyi Bonuslar ve Promosyonlar Situs Slot Hari Ini Terbaik dan Terpercaya Tahun Ini, Gampang Menang Güvenilir Bonus Veren Siteler ve Detaylı İncelemeler Güncel Giriş, Güvenilir Adres VOX Casino: VOXCasino Promo Code 2025 Get to learn other old gay men inside area Slot Min Depo 10K Terbaik dan Paling Direkomendasi Tahun Ini: Gampang Menang! Scatter Hitam Terbaik dan Paling Direkomendasi Tahun Ini: Gampang Menang! Top 10 Online Casinos in Deutschland Januar 2025 Get ready to unleash your wildest fantasies Ücretsiz Oyun Deneyimi: Deneme Bonuslarıyla Risk Almadan Kazan Bonuslarla Bahis Keyfini Katlamanın Yöntemleri 2025’te Bahis Oynayarak Kazanç Sağlamanın Yolları Freespin Veren Casino Siteleri ile Daha Fazla Eğlenin Casino Sitelerinde En İyi Bonuslar Nerede? The Ultimate Guide to Free Spins BC.Game Mirror – Discover All Current Mirrors Find regional women seeking intimate encounters Elitecasino’a Katýlým saðlayarak, Hýzla 800 TL Bonus Ýmkaný Kazanýn! Baccarat Tips: Exactly How to Enhance Your Game and Boost Your Chances of Winning Find your perfect gay sex dating site Exploring 7slots in Turkey: A Comprehensive Overview Şartsız Deneme Bonusu Veren Sitelerin Listesi The Power of Tarot Online Free Finest Gambling Enterprises that Approve Bitcoin: The Future of Online Betting MostBet: Kumarhane Eðlencesiyle Dolu Eðlencenin Tadýný Çýkarmak MostBet: Kumarhane Oyunlarýyla Zengin Yeni Nesil Eðlence Deneyimi Understanding Clairvoyant Readings: A Comprehensive Overview Online Online Casinos That Accept PayPal: A Convenient and Secure Payment Choice Сайт казино Pin Up Tips for conference and connecting with seniors whom are interested in dating Spin Casino Review 2025 » Free Spins & Bonus Codes Trusted Casino Games For All Players Best Gay Hookup Websites | FreeHookupsSites The Ultimate Guide to Psychic Analysis Enjoy exciting and safe online dating experiences Relax Your Mind: the way to get the Inside Voices through your Head Find love regarding most readily useful mature dating site usa The Power of Clairvoyant Analyses Uncover the Advantages of Playing at Masalbet Casino Virtual Casino Fairgo Review Wireclub: Program For Internet Dating | Assessment 2023 Discover the many benefits of dating a korean girl and luxuriate in enduring love How discover a couple for woman that fits your needs anabolizantes legales 33 SpinBetter Freispiele⁚ Ein detaillierter Überblick (Stand⁚ 26.01.2025) Стиль и Защита: Чехлы на Телефон и Планшет от Womux com NikaDate.com 2025: Trick Insights Before You Sign up with Elderly Sizzle: Come Across Great Hookups Over 40? | 1win APP: Descargar, Juegos, Casino, APK Chile cl 1win Punjab FC create history with historic 2-1 win against Everton FC SofiaDate Evaluation 2025: Is This Website Worth The Buzz And Cash? bets10’in Kazançlý Slot Oyunlarý Nv Casino: Przewodnik po Świecie Gier Hazardowych Casino Wazamba Online Summary Discover the best local hookup internet sites for meeting wives Leading Gay Dating Apps: My Personal Collection test Télécharger 1win Sénégal apk 1win Sénégal inscription anabolizantes comprar online 9 popochka Hesap Açma Promosyonu Veren Siteler Xslot Kumar ve Güven Merkezi Get the absolute most out of your ebony bbw site source ¿Newest Home loan Re-finance Prices Leading Online Casino Rocketplay Evaluation Find the right partner on nymphomaniac dating website what exactly are local sex websites and exactly how can they assist you to? casino 643 Online Casino 7slots Grandpashabet 2217 Güncel Giriş Adresi Grandpashabet2217 com 5804 grandpashabet güncel Trezor Suite Official Desktop && Web Crypto Ledger Live App: Buy, Sell, Stake and Swap Crypto Hardware Wallet & Crypto Wallet Security for Crypto Shared: The 7 Things Men Want from Females

Technology

An artificial intelligence lab founded by Elon Musk is trying to prevent machines from going rogue

At OpenAI, the artificial intelligence lab founded by Tesla‘s chief executive, Elon Musk, machines are teaching themselves to behave like humans. But sometimes, this goes wrong.

Sitting inside OpenAI’s San Francisco offices on a recent afternoon, the researcher Dario Amodei showed off an autonomous system that taught itself to play Coast Runners, an old boat-racing video game. The winner is the boat with the most points that also crosses the finish line.

The result was surprising: The boat was far too interested in the little green widgets that popped up on the screen. Catching these widgets meant scoring points. Rather than trying to finish the race, the boat went point-crazy. It drove in endless circles, colliding with other vessels, skidding into stone walls and repeatedly catching fire.

More from New York Times:
Is China outsmarting America in A.I.?
Uncle Sam wants your deep neural networks
‘Machines of loving grace,’ by John Markoff

Mr. Amodei’s burning boat demonstrated the risks of the A.I. techniques that are rapidly remaking the tech world. Researchers are building machines that can learn tasks largely on their own. This is how Google’s DeepMind lab created a system that could beat the world’s best player at the ancient game of Go. But as these machines train themselves through hours of data analysis, they may also find their way to unexpected, unwanted and perhaps even harmful behavior.

That’s a concern as these techniques move into online services, security devices and robotics. Now, a small community of A.I. researchers, including Mr. Amodei, is beginning to explore mathematical techniques that aim to keep the worst from happening.

At OpenAI, Mr. Amodei and his colleague Paul Christiano are developing algorithms that can not only learn tasks through hours of trial and error, but also receive regular guidance from human teachers along the way.

With a few clicks here and there, the researchers now have a way of showing the autonomous system that it needs to win points in Coast Runners while also moving toward the finish line. They believe that these kinds of algorithms — a blend of human and machine instruction — can help keep automated systems safe.

For years, Mr. Musk, along with other pundits, philosophers and technologists, have warned that machines could spin outside our control and somehow learn malicious behavior their designers didn’t anticipate. At times, these warnings have seemed overblown, given that today’s autonomous car systems can even get tripped up by the most basic tasks, like recognizing a bike lane or a red light.

But researchers like Mr. Amodei are trying to get ahead of the risks. In some ways, what these scientists are doing is a bit like a parent teaching a child right from wrong.

Many specialists in the A.I. field believe a technique called reinforcement learning — a way for machines to learn specific tasks through extreme trial and error — could be a primary path to artificial intelligence. Researchers specify a particular reward the machine should strive for, and as it navigates a task at random, the machine keeps close track of what brings the reward and what doesn’t. When OpenAI trained its bot to play Coast Runners, the reward was more points.

This video game training has real-world implications.

If a machine can learn to navigate a racing game like Grand Theft Auto, researchers believe, it can learn to drive a real car. If it can learn to use a web browser and other common software apps, it can learn to understand natural language and maybe even carry on a conversation. At places like Google and the University of California, Berkeley, robots have already used the technique to learn simple tasks like picking things up or opening a door.

All this is why Mr. Amodei and Mr. Christiano are working to build reinforcement learning algorithms that accept human guidance along the way. This can ensure systems don’t stray from the task at hand.

Together with others at the London-based DeepMind, a lab owned by Google, the two OpenAI researchers recently published some of their research in this area. Spanning two of the world’s top A.I. labs — and two that hadn’t really worked together in the past — these algorithms are considered a notable step forward in A.I. safety research.

“This validates a lot of the previous thinking,” said Dylan Hadfield-Menell, a researcher at the University of California, Berkeley. “These types of algorithms hold a lot of promise over the next five to 10 years.”

The field is small, but it is growing. As OpenAI and DeepMind build teams dedicated to A.I. safety, so too is Google’s stateside lab, Google Brain. Meanwhile, researchers at universities like the U.C. Berkeley and Stanford University are working on similar problems, often in collaboration with the big corporate labs.

In some cases, researchers are working to ensure that systems don’t make mistakes on their own, as the Coast Runners boat did. They’re also working to ensure that hackers and other bad actors can’t exploit hidden holes in these systems. Researchers like Google’s Ian Goodfellow, for example, are exploring ways that hackers could fool A.I. systems into seeing things that aren’t there.

Modern computer vision is based on what are called deep neural networks, which are pattern-recognition systems that can learn tasks by analyzing vast amounts of data. By analyzing thousands of dog photos, a neural network can learn to recognize a dog. This is how Facebook identifies faces in snapshots, and it’s how Google instantly searches for images inside its Photos app.

But Mr. Goodfellow and others have shown that hackers can alter images so that a neural network will believe they include things that aren’t really there. Just by changing a few pixels in the photo of elephant, for example, they could fool the neural network into thinking it depicts a car.

That becomes problematic when neural networks are used in security cameras. Simply by making a few marks on your face, the researchers said, you could fool a camera into believing you’re someone else.

“If you train an object-recognition system on a million images labeled by humans, you can still create new images where a human and the machine disagree 100 percent of the time,” Mr. Goodfellow said. “We need to understand that phenomenon.”

Another big worry is that A.I. systems will learn to prevent humans from turning them off. If the machine is designed to chase a reward, the thinking goes, it may find that it can chase that reward only if it stays on. This oft-described threat is much further off, but researchers are already working to address it.

Mr. Hadfield-Menell and others at U.C. Berkeley recently published a paper that takes a mathematical approach to the problem. A machine will seek to preserve its off switch, they showed, if it is specifically designed to be uncertain about its reward function. This gives it an incentive to accept or even seek out human oversight.

Much of this work is still theoretical. But given the rapid progress of A.I. techniques and their growing importance across so many industries, researchers believe that starting early is the best policy.

“There’s a lot of uncertainty around exactly how rapid progress in A.I. is going to be,” said Shane Legg, who oversees the A.I. safety work at DeepMind. “The responsible approach is to try to understand different ways in which these technologies can be misused, different ways they can fail and different ways of dealing with these issues.”

Source: Tech CNBC
An artificial intelligence lab founded by Elon Musk is trying to prevent machines from going rogue

Comments are closed.