Tag Archives: human

#436573 This Week’s Awesome Tech Stories From ...

ARTIFICIAL INTELLIGENCE
The Messy, Secretive Reality Behind OpenAI’s Bid to Save the World
Karen Hao | MIT Technology Review
“The AI moonshot was founded in the spirit of transparency. This is the inside story of how competitive pressure eroded that idealism. …Yet OpenAI is still a bastion of talent and cutting-edge research, filled with people who are sincerely striving to work for the benefit of humanity. In other words, it still has the most important elements, and there’s still time for it to change.”

ROBOTICS
3D Printed Four-Legged Robot Is Ready to Take on Spot—at a Lower Price
Luke Dormehl | Digital Trends
“[Ghost Robotics and Origin] have teamed up to develop a new line of robots, called the Spirit Series, which offer impressively capable four-legged robots, but which can be printed using additive manufacturing at a fraction of the cost and speed of traditional manufacturing approaches.”

PRIVACY
The Studs on This Punk Bracelet Are Actually Microphone-Jamming Ultrasonic Speakers
Andrew Liszewski | Gizmodo
“You can prevent facial recognition cameras from identifying you by wearing face paint, masks, or sometimes just a pair of oversized sunglasses. Keeping conversations private from an ever-growing number of microphone-equipped devices isn’t quite as easy, but researchers have created what could be the first wearable that actually helps increase your privacy.”

TRANSPORTATION
Iron Man Dreams Are Closer to Becoming a Reality Thanks to This New Jetman Dubai Video
Julia Alexander | The Verge
“Tony Stark may have destroyed his Iron Man suits in Iron Man 3 (only to bring out a whole new line in Avengers: Age of Ultron), but Jetman Dubai’s Iron Man-like dreams of autonomous human flight are realer than ever. A new video published by the company shows pilot Vince Reffet using a jet-powered, carbon-fiber suit to launch off the ground and fly 6,000 feet in the air.”

TECHNOLOGY
Wikipedia Is the Last Best Place on the Internet
Richard Cooke | Wired
“More than an encyclopedia, Wikipedia has become a community, a library, a constitution, an experiment, a political manifesto—the closest thing there is to an online public square. It is one of the few remaining places that retains the faintly utopian glow of the early World Wide Web.”

SCIENCE
The Very Large Array Will Search for Evidence of Extraterrestrial Life
Georgina Torbet | Digital Trends
“To begin the project, an interface will be added to the NRAO’s Very Large Array (VLA) in New Mexico to search for events or structures which could indicate the presence of life, such as laser beams, structures built around stars, indications of constructed satellites, or atmospheric chemicals produced by industry.”

SCIENCE FICTION
The Terrible Truth About Star Trek’s Transporters
Cassidy Ward | SyFy Wire
“The fact that you are scanned, deconstructed, and rebuilt almost immediately thereafter only creates the illusion of continuity. In reality, you are killed and then something exactly like you is born, elsewhere. There’s a whole philosophical debate about whether this really matters. If the person constructed on the other end is identical to you, down to the atomic level, is there any measurable difference from it being actually you?”

Image Credit: Samuel Giacomelli / Unsplash Continue reading

Posted in Human Robots

#436559 This Is What an AI Said When Asked to ...

“What’s past is prologue.” So says the famed quote from Shakespeare’s The Tempest, alleging that we can look to what has already happened as an indication of what will happen next.

This idea could be interpreted as being rather bleak; are we doomed to repeat the errors of the past until we correct them? We certainly do need to learn and re-learn life lessons—whether in our work, relationships, finances, health, or other areas—in order to grow as people.

Zooming out, the same phenomenon exists on a much bigger scale—that of our collective human history. We like to think we’re improving as a species, but haven’t yet come close to doing away with the conflicts and injustices that plagued our ancestors.

Zooming back in (and lightening up) a little, what about the short-term future? What might happen over the course of this year, and what information would we use to make educated guesses about it?

The editorial team at The Economist took a unique approach to answering these questions. On top of their own projections for 2020, including possible scenarios in politics, economics, and the continued development of technologies like artificial intelligence, they looked to an AI to make predictions of its own. What it came up with is intriguing, and a little bit uncanny.

[For the full list of the questions and answers, read The Economist article].

An AI That Reads—Then Writes
Almost exactly a year ago, non-profit OpenAI announced it had built a neural network for natural language processing called GPT-2. The announcement was met with some controversy, as it included the caveat that the tool would not be immediately released to the public due to its potential for misuse. It was then released in phases over the course of several months.

GPT-2’s creators upped the bar on quality when training the neural net; rather than haphazardly feeding it low-quality text, they only used articles that got more than three upvotes on Reddit (admittedly, this doesn’t guarantee high quality across the board—but it’s something).

The training dataset consisted of 40GB of text. For context, 1GB of text is about 900,000 ASCII pages or 130,000 double-spaced Microsoft Word pages.

The tool has no understanding of the text it’s generating, of course. It uses language patterns and word sequences to draw statistical associations between words and phrases, building a sort of guidebook for itself (not unlike the grammar rules and vocabulary words you might study when trying to learn a foreign language). It then uses that guidebook to answer questions or predict what will come after a particular sequence of words.

GPT-2’s creators did note that when the model is trained on specifically-selected datasets for narrower applications, its replies become more convincing.

Some Light Editing
Though the Economist article detailing GPT-2’s predictions describes the text the model generated as “unedited,” this isn’t wholly accurate. In a Medium post, deputy editor Tom Standage describes the methodology he used, and it does involve a degree of tweaking.

Standage wrote an introductory paragraph, followed by his opening question (“Greetings, GPT-2. Have you done an interview before?”). He configured the tool to generate five responses to each subsequent question then selected the best answer, deleting any questions GPT-2 came up with as part of its response.

AI’s View of the World—and Itself
The questions Standage asked ranged from tech-related (the future of AI, technological unemployment, misuse of technology) to political and economic (re-election of Donald Trump, the US-China trade war). Here are a couple of his questions and GPT-2’s answers:

Q: Do fake news stories, generated using AI, pose a threat to democracy? Are we likely to see this tactic being used in the 2020 American presidential elections?
A: Yes, we’ll probably see them. It’s just a matter of when. Fake news stories are generally generated by political campaigns, and have the potential to have a huge impact on the outcome of an election. This is because they spread misinformation, often with no basis in fact.

Q: How do you see the economic outlook for 2020?
A: I think it is very unclear. The outlook for the UK economy is uncertain, but the American economy is very strong. I think we are going to have a lot of turbulence in the world economy.

While some of its answers seemed insightful—when asked about the future of AI, GPT-2 advised that we treat the technology like a tool and “put as much effort into developing [it] as necessary, rather than worrying that it’s going to harm us and destroy our lives”—many of the responses were quite vague. One answer, for example, mentions that there will “probably be major changes in China.” Are we talking political changes? Social? Economic? All of the above?

However, while nothing the AI wrote was particularly illuminating or new, it’s impressive that it was able to expound on the correct topic for each question, and in fully coherent English.

GPT-2 named itself—AI—as the most important disruptive technology to watch in 2020. This is telling; it’s coming from a synthesis of millions of pages of published articles. If GPT-2 thinks AI is more important than, say, gene editing or quantum computing, it could be right. Or it could simply be that AI is at peak hype, and as such more is being written about it than about other technologies.

Equally intriguing was GPT-2’s response when asked whether Donald Trump will win a second term: “I think he will not win a second term. I think he will be defeated in the general election.” Some deeper insight there would be great, but hey—we’ll take it.

Predicting Predictions
Since an AI can read and synthesize vast data sets much faster than we can, it’s being used to predict all kinds of things, from virus outbreaks to crime. But asking it to philosophize on the future based on the (Reddit-curated) past is new, and if you think about it, a pretty fascinating undertaking.

As GPT-2 and tools like it continually improve, we’ll likely see them making more—and better—predictions of the future. In the meantime, let’s hope that the new data these models are trained on—news of what’s happening this week, this month, this year—add to an already-present sense of optimism.

When asked if it had any advice for readers, GPT-2 replied, “The big projects that you think are impossible today are actually possible in the near future.”

Image Credit: Alexas_Fotos from Pixabay Continue reading

Posted in Human Robots

#436546 How AI Helped Predict the Coronavirus ...

Coronavirus has been all over the news for the last couple weeks. A dedicated hospital sprang up in just eight days, the stock market took a hit, Chinese New Year celebrations were spoiled, and travel restrictions are in effect.

But let’s rewind a bit; some crucial events took place before we got to this point.

A little under two weeks before the World Health Organization (WHO) alerted the public of the coronavirus outbreak, a Canadian artificial intelligence company was already sounding the alarm. BlueDot uses AI-powered algorithms to analyze information from a multitude of sources to identify disease outbreaks and forecast how they may spread. On December 31st 2019, the company sent out a warning to its customers to avoid Wuhan, where the virus originated. The WHO didn’t send out a similar public notice until January 9th, 2020.

The story of BlueDot’s early warning is the latest example of how AI can improve our identification of and response to new virus outbreaks.

Predictions Are Bad News
Global pandemic or relatively minor scare? The jury is still out on the coronavirus. However, the math points to signs that the worst is yet to come.

Scientists are still working to determine how infectious the virus is. Initial analysis suggests it may be somewhere between influenza and polio on the virus reproduction number scale, which indicates how many new cases one case leads to.

UK and US-based researchers have published a preliminary paper estimating that the confirmed infected people in Wuhan only represent five percent of those who are actually infected. If the models are correct, 190,000 people in Wuhan will be infected by now, major Chinese cities are on the cusp of large-scale outbreaks, and the virus will continue to spread to other countries.

Finding the Start
The spread of a given virus is partly linked to how long it remains undetected. Identifying a new virus is the first step towards mobilizing a response and, in time, creating a vaccine. Warning at-risk populations as quickly as possible also helps with limiting the spread.

These are among the reasons why BlueDot’s achievement is important in and of itself. Furthermore, it illustrates how AIs can sift through vast troves of data to identify ongoing virus outbreaks.

BlueDot uses natural language processing and machine learning to scour a variety of information sources, including chomping through 100,000 news reports in 65 languages a day. Data is compared with flight records to help predict virus outbreak patterns. Once the automated data sifting is completed, epidemiologists check that the findings make sense from a scientific standpoint, and reports are sent to BlueDot’s customers, which include governments, businesses, and public health organizations.

AI for Virus Detection and Prevention
Other companies, such as Metabiota, are also using data-driven approaches to track the spread of the likes of the coronavirus.

Researchers have trained neural networks to predict the spread of infectious diseases in real time. Others are using AI algorithms to identify how preventive measures can have the greatest effect. AI is also being used to create new drugs, which we may well see repeated for the coronavirus.

If the work of scientists Barbara Han and David Redding comes to fruition, AI and machine learning may even help us predict where virus outbreaks are likely to strike—before they do.

The Uncertainty Factor
One of AI’s core strengths when working on identifying and limiting the effects of virus outbreaks is its incredibly insistent nature. AIs never tire, can sift through enormous amounts of data, and identify possible correlations and causations that humans can’t.

However, there are limits to AI’s ability to both identify virus outbreaks and predict how they will spread. Perhaps the best-known example comes from the neighboring field of big data analytics. At its launch, Google Flu Trends was heralded as a great leap forward in relation to identifying and estimating the spread of the flu—until it underestimated the 2013 flu season by a whopping 140 percent and was quietly put to rest.

Poor data quality was identified as one of the main reasons Google Flu Trends failed. Unreliable or faulty data can wreak havoc on the prediction power of AIs.

In our increasingly interconnected world, tracking the movements of potentially infected individuals (by car, trains, buses, or planes) is just one vector surrounded by a lot of uncertainty.

The fact that BlueDot was able to correctly identify the coronavirus, in part due to its AI technology, illustrates that smart computer systems can be incredibly useful in helping us navigate these uncertainties.

Importantly, though, this isn’t the same as AI being at a point where it unerringly does so on its own—which is why BlueDot employs human experts to validate the AI’s findings.

Image Credit: Coronavirus molecular illustration, Gianluca Tomasello/Wikimedia Commons Continue reading

Posted in Human Robots

#436526 Not Bot, Not Beast: Scientists Create ...

A remarkable combination of artificial intelligence (AI) and biology has produced the world’s first “living robots.”

This week, a research team of roboticists and scientists published their recipe for making a new lifeform called xenobots from stem cells. The term “xeno” comes from the frog cells (Xenopus laevis) used to make them.

One of the researchers described the creation as “neither a traditional robot nor a known species of animal,” but a “new class of artifact: a living, programmable organism.”

Xenobots are less than 1 millimeter long and made of 500-1,000 living cells. They have various simple shapes, including some with squat “legs.” They can propel themselves in linear or circular directions, join together to act collectively, and move small objects. Using their own cellular energy, they can live up to 10 days.

While these “reconfigurable biomachines” could vastly improve human, animal, and environmental health, they raise legal and ethical concerns.

Strange New ‘Creature’
To make xenobots, the research team used a supercomputer to test thousands of random designs of simple living things that could perform certain tasks.

The computer was programmed with an AI “evolutionary algorithm” to predict which organisms would likely display useful tasks, such as moving towards a target.

After the selection of the most promising designs, the scientists attempted to replicate the virtual models with frog skin or heart cells, which were manually joined using microsurgery tools. The heart cells in these bespoke assemblies contract and relax, giving the organisms motion.

The creation of xenobots is groundbreaking. Despite being described as “programmable living robots,” they are actually completely organic and made of living tissue. The term “robot” has been used because xenobots can be configured into different forms and shapes, and “programmed” to target certain objects, which they then unwittingly seek. They can also repair themselves after being damaged.

Possible Applications
Xenobots may have great value. Some speculate they could be used to clean our polluted oceans by collecting microplastics. Similarly, they may be used to enter confined or dangerous areas to scavenge toxins or radioactive materials. Xenobots designed with carefully shaped “pouches” might be able to carry drugs into human bodies.

Future versions may be built from a patient’s own cells to repair tissue or target cancers. Being biodegradable, xenobots would have an edge on technologies made of plastic or metal.

Further development of biological “robots” could accelerate our understanding of living and robotic systems. Life is incredibly complex, so manipulating living things could reveal some of life’s mysteries—and improve our use of AI.

Legal and Ethical Questions
Conversely, xenobots raise legal and ethical concerns. In the same way they could help target cancers, they could also be used to hijack life functions for malevolent purposes.

Some argue artificially making living things is unnatural, hubristic, or involves “playing God.” A more compelling concern is that of unintended or malicious use, as we have seen with technologies in fields including nuclear physics, chemistry, biology and AI. For instance, xenobots might be used for hostile biological purposes prohibited under international law.

More advanced future xenobots, especially ones that live longer and reproduce, could potentially “malfunction” and go rogue, and out-compete other species.

For complex tasks, xenobots may need sensory and nervous systems, possibly resulting in their sentience. A sentient programmed organism would raise additional ethical questions. Last year, the revival of a disembodied pig brain elicited concerns about different species’ suffering.

Managing Risks
The xenobot’s creators have rightly acknowledged the need for discussion around the ethics of their creation. The 2018 scandal over using CRISPR (which allows the introduction of genes into an organism) may provide an instructive lesson here. While the experiment’s goal was to reduce the susceptibility of twin baby girls to HIV-AIDS, associated risks caused ethical dismay. The scientist in question is in prison.

When CRISPR became widely available, some experts called for a moratorium on heritable genome editing. Others argued the benefits outweighed the risks.

While each new technology should be considered impartially and based on its merits, giving life to xenobots raises certain significant questions:

Should xenobots have biological kill-switches in case they go rogue?
Who should decide who can access and control them?
What if “homemade” xenobots become possible? Should there be a moratorium until regulatory frameworks are established? How much regulation is required?

Lessons learned in the past from advances in other areas of science could help manage future risks, while reaping the possible benefits.

Long Road Here, Long Road Ahead
The creation of xenobots had various biological and robotic precedents. Genetic engineering has created genetically modified mice that become fluorescent in UV light.

Designer microbes can produce drugs and food ingredients that may eventually replace animal agriculture. In 2012, scientists created an artificial jellyfish called a “medusoid” from rat cells.

Robotics is also flourishing. Nanobots can monitor people’s blood sugar levels and may eventually be able to clear clogged arteries. Robots can incorporate living matter, which we witnessed when engineers and biologists created a sting-ray robot powered by light-activated cells.

In the coming years, we are sure to see more creations like xenobots that evoke both wonder and due concern. And when we do, it is important we remain both open-minded and critical.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

Image Credit: Photo by Joel Filipe on Unsplash Continue reading

Posted in Human Robots

#436507 The Weird, the Wacky, the Just Plain ...

As you know if you’ve ever been to, heard of, or read about the annual Consumer Electronics Show in Vegas, there’s no shortage of tech in any form: gadgets, gizmos, and concepts abound. You probably couldn’t see them all in a month even if you spent all day every day trying.

Given the sheer scale of the show, the number of exhibitors, and the inherent subjectivity of bestowing superlatives, it’s hard to pick out the coolest tech from CES. But I’m going to do it anyway; in no particular order, here are some of the products and concepts that I personally found most intriguing at this year’s event.

e-Novia’s Haptic Gloves
Italian startup e-Novia’s Weart glove uses a ‘sensing core’ to record tactile sensations and an ‘actuation core’ to reproduce those sensations onto the wearer’s skin. Haptic gloves will bring touch to VR and AR experiences, making them that much more life-like. The tech could also be applied to digitization of materials and in gaming and entertainment.

e-Novia’s modular haptic glove
I expected a full glove, but in fact there were two rings that attached to my fingers. Weart co-founder Giovanni Spagnoletti explained that they’re taking a modular approach, so as to better tailor the technology to different experiences. He then walked me through a virtual reality experience that was a sort of simulated science experiment: I had to lift a glass beaker, place it on a stove, pour in an ingredient, open a safe to access some dry ice, add that, and so on. As I went through the steps, I felt the beaker heat up and cool off at the expected times, and felt the liquid moving inside, as well as the pressure of my fingertips against the numbered buttons on the safe.

A virtual (but tactile) science experiment
There was a slight delay between my taking an action and feeling the corresponding tactile sensation, but on the whole, the haptic glove definitely made the experience more realistic—and more fun. Slightly less fun but definitely more significant, Spagnoletti told me Weart is working with a medical group to bring tactile sensations to VR training for surgeons.

Sarcos Robotics’ Exoskeleton
That tire may as well be a feather
Sarcos Robotics unveiled its Guardian XO full-body exoskeleton, which it says can safely lift up to 200 pounds across an extended work session. What’s cool about this particular exoskeleton is that it’s not just a prototype; the company announced a partnership with Delta airlines, which will be trialing the technology for aircraft maintenance, engine repair, and luggage handling. In a demo, I watched a petite female volunteer strap into the exoskeleton and easily lift a 50-pound weight with one hand, and a Sarcos employee lift and attach a heavy component of a propeller; she explained that the strength-augmenting function of the exoskeleton can easily be switched on or off—and the wearer’s hands released—to facilitate multi-step tasks.

Hyundai’s Flying Taxi
Where to?
Hyundai and Uber partnered to unveil an air taxi concept. With a 49-foot wingspan, 4 lift rotors, and 4 tilt rotors, the aircraft would be manned by a pilot and could carry 4 passengers at speeds up to 180 miles per hour. The companies say you’ll be able to ride across your city in one of these by 2030—we’ll see if the regulatory environment, public opinion, and other factors outside of technological capability let that happen.

Mercedes’ Avatar Concept Car
Welcome to the future
As evident from its name, Mercedes’ sweet new Vision AVTR concept car was inspired by the movie Avatar; director James Cameron helped design it. The all-electric car has no steering wheel, transparent doors, seats made of vegan leather, and 33 reptilian-scale-like flaps on the back; its design is meant to connect the driver with both the car and the surrounding environment in a natural, seamless way.

Next-generation scrolling
Offered the chance to ‘drive’ the car, I jumped on it. Placing my hand on the center console started the engine, and within seconds it had synced to my heartbeat, which reverberated through the car. The whole dashboard, from driver door to passenger door, is one big LED display. It showed a virtual landscape I could select by holding up my hand: as I moved my hand from left to right, different images were projected onto my open palm. Closing my hand on an image selected it, and suddenly it looked like I was in the middle of a lush green mountain range. Applying slight forward pressure on the center console made the car advance in the virtual landscape; it was essentially like playing a really cool video game.

Mercedes is aiming to have a carbon-neutral production fleet by 2039, and to reduce the amount of energy it uses during production by 40 percent by 2030. It’s unclear when—or whether—the man-machine-nature connecting features of the Vision AVTR will start showing up in production, but I for one will be on the lookout.

Waverly Labs’ In-Ear Translator
Waverly Labs unveiled its Ambassador translator earlier this year and has it on display at the show. It’s worn on the ear and uses a far-field microphone array with speech recognition to translate real-time conversations in 20 different languages. Besides in-ear audio, translations can also appear as text on an app or be broadcast live in a conference environment.

It’s kind of like a giant talking earring
I stopped by the booth and tested out the translator with Waverly senior software engineer Georgiy Konovalov. We each hooked on an earpiece, and first, he spoke to me in Russian. After a delay of a couple seconds, I heard his words in—slightly robotic, but fully comprehensible—English. Then we switched: I spoke to him in Spanish, my words popped up on his phone screen in Cyrillic, and he translated them back to English for me out loud.

On the whole, the demo was pretty cool. If you’ve ever been lost in a foreign country whose language you don’t speak, imagine how handy a gadget like this would come in. Let’s just hope that once they’re more widespread, these products don’t end up discouraging people from learning languages.

Not to be outdone, Google also announced updates to its Translate product, which is being deployed at information desks in JFK airport’s international terminal, in sports stadiums in Qatar, and by some large hotel chains.

Stratuscent’s Digital Nose
AI is making steady progress towards achieving human-like vision and hearing—but there’s been less work done on mimicking our sense of smell (maybe because it’s less useful in everyday applications). Stratuscent’s digital nose, which it says is based on NASA patents, uses chemical receptors and AI to identify both simple chemicals and complex scents. The company is aiming to create the world’s first comprehensive database of everyday scents, which it says it will use to make “intelligent decisions” for customers. What kind of decisions remains to be seen—and smelled.

Banner Image Credit: The Mercedes Vision AVTR concept car. Photo by Vanessa Bates Ramirez Continue reading

Posted in Human Robots