Tag Archives: did

#437103 How to Make Sense of Uncertainty in a ...

As the internet churns with information about Covid-19, about the virus that causes the disease, and about what we’re supposed to do to fight it, it can be difficult to see the forest for the trees. What can we realistically expect for the rest of 2020? And how do we even know what’s realistic?

Today, humanity’s primary, ideal goal is to eliminate the virus, SARS-CoV-2, and Covid-19. Our second-choice goal is to control virus transmission. Either way, we have three big aims: to save lives, to return to public life, and to keep the economy functioning.

To hit our second-choice goal—and maybe even our primary goal—countries are pursuing five major public health strategies. Note that many of these advances cross-fertilize: for example, advances in virus testing and antibody testing will drive data-based prevention efforts.

Five major public health strategies are underway to bring Covid-19 under control and to contain the spread of SARS-CoV-2.
These strategies arise from things we can control based on the things that we know at any given moment. But what about the things we can’t control and don’t yet know?

The biology of the virus and how it interacts with our bodies is what it is, so we should seek to understand it as thoroughly as possible. How long any immunity gained from prior infection lasts—and indeed whether people develop meaningful immunity at all after infection—are open questions urgently in need of greater clarity. Similarly, right now it’s important to focus on understanding rather than making assumptions about environmental factors like seasonality.

But the biggest question on everyone’s lips is, “When?” When will we see therapeutic progress against Covid-19? And when will life get “back to normal”? There are lots of models out there on the internet; which of those models are right? The simple answer is “none of them.” That’s right—it’s almost certain that every model you’ve seen is wrong in at least one detail, if not all of them. But modeling is meant to be a tool for deeper thinking, a way to run mental (and computational) experiments before—and while—taking action. As George E. P. Box famously wrote in 1976, “All models are wrong, but some are useful.”

Here, we’re seeking useful insights, as opposed to exact predictions, which is why we’re pulling back from quantitative details to get at the mindsets that will support agency and hope. To that end, I’ve been putting together timelines that I believe will yield useful expectations for the next year or two—and asking how optimistic I need to be in order to believe a particular timeline.

For a moderately optimistic scenario to be relevant, breakthroughs in science and technology come at paces expected based on previous efforts and assumptions that turn out to be basically correct; accessibility of those breakthroughs increases at a reasonable pace; regulation achieves its desired effects, without major surprises; and compliance with regulations is reasonably high.

In contrast, if I’m being highly optimistic, breakthroughs in science and technology and their accessibility come more quickly than they ever have before; regulation is evidence-based and successful in the first try or two; and compliance with those regulations is high and uniform. If I’m feeling not-so-optimistic, then I anticipate serious setbacks to breakthroughs and accessibility (with the overturning of many important assumptions), repeated failure of regulations to achieve their desired outcomes, and low compliance with those regulations.

The following scenarios outline the things that need to happen in the fight against Covid-19, when I expect to see them, and how confident I feel in those expectations. They focus on North America and Europe because there are data missing about China’s 2019 outbreak and other regions are still early in their outbreaks. Perhaps the most important thing to keep in mind throughout: We know more today than we did yesterday, but we still have much to learn. New knowledge derived from greater study and debate will almost certainly inspire ongoing course corrections.

As you dive into the scenarios below, practice these three mindset shifts. First, defeating Covid-19 will be a marathon, not a sprint. We shouldn’t expect life to look like 2019 for the next year or two—if ever. As Ed Yong wrote recently in The Atlantic, “There won’t be an obvious moment when everything is under control and regular life can safely resume.” Second, remember that you have important things to do for at least a year. And third, we are all in this together. There is no “us” and “them.” We must all be alert, responsive, generous, and strong throughout 2020 and 2021—and willing to throw away our assumptions when scientific evidence invalidates them.

The Middle Way: Moderate Optimism
Let’s start with the case in which I have the most confidence: moderate optimism.

This timeline considers milestones through late 2021, the earliest that I believe vaccines will become available. The “normal” timeline for developing a vaccine for diseases like seasonal flu is 18 months, which leads to my projection that we could potentially have vaccines as soon as 18 months from the first quarter of 2020. While Melinda Gates agrees with that projection, others (including AI) believe that 3 to 5 years is far more realistic, based on past vaccine development and the need to test safety and efficacy in humans. However, repurposing existing vaccines against other diseases—or piggybacking off clever synthetic platforms—could lead to vaccines being available sooner. I tried to balance these considerations for this moderately optimistic scenario. Either way, deploying vaccines at the end of 2021 is probably much later than you may have been led to believe by the hype engine. Again, if you take away only one message from this article, remember that the fight against Covid-19 is a marathon, not a sprint.

Here, I’ve visualized a moderately optimistic scenario as a baseline. Think of these timelines as living guides, as opposed to exact predictions. There are still many unknowns. More or less optimistic views (see below) and new information could shift these timelines forward or back and change the details of the strategies.
Based on current data, I expect that the first wave of Covid-19 cases (where we are now) will continue to subside in many areas, leading governments to ease restrictions in an effort to get people back to work. We’re already seeing movement in that direction, with a variety of benchmarks and changes at state and country levels around the world. But depending on the details of the changes, easing restrictions will probably cause a second wave of sickness (see Germany and Singapore), which should lead governments to reimpose at least some restrictions.

In tandem, therapeutic efforts will be transitioning from emergency treatments to treatments that have been approved based on safety and efficacy data in clinical trials. In a moderately optimistic scenario, assuming clinical trials currently underway yield at least a few positive results, this shift to mostly approved therapies could happen as early as the third or fourth quarter of this year and continue from there. One approval that should come rather quickly is for plasma therapies, in which the blood from people who have recovered from Covid-19 is used as a source of antibodies for people who are currently sick.

Companies around the world are working on both viral and antibody testing, focusing on speed, accuracy, reliability, and wide accessibility. While these tests are currently being run in hospitals and research laboratories, at-home testing is a critical component of the mass testing we’ll need to keep viral spread in check. These are needed to minimize the impact of asymptomatic cases, test the assumption that infection yields resistance to subsequent infection (and whether it lasts), and construct potential immunity passports if this assumption holds. Testing is also needed for contact tracing efforts to prevent further spread and get people back to public life. Finally, it’s crucial to our fundamental understanding of the biology of SARS-CoV-2 and Covid-19.

We need tests that are very reliable, both in the clinic and at home. So, don’t go buying any at-home test kits just yet, even if you find them online. Wait for reliable test kits and deeper understanding of how a test result translates to everyday realities. If we’re moderately optimistic, in-clinic testing will rapidly expand this quarter and/or next, with the possibility of broadly available, high-quality at-home sampling (and perhaps even analysis) thereafter.

Note that testing is not likely to be a “one-and-done” endeavor, as a person’s infection and immunity status change over time. Expect to be testing yourself—and your family—often as we move later into 2020.

Testing data are also going to inform distancing requirements at the country and local levels. In this scenario, restrictions—at some level of stringency—could persist at least through the end of 2020, as most countries are way behind the curve on testing (Iceland is an informative exception). Governments will likely continue to ask citizens to work from home if at all possible; to wear masks or face coverings in public; to employ heightened hygiene and social distancing in workplaces; and to restrict travel and social gatherings. So while it’s likely we’ll be eating in local restaurants again in 2020 in this scenario, at least for a little while, it’s not likely we’ll be heading to big concerts any time soon.

The Extremes: High and Low Optimism
How would high and low levels of optimism change our moderately optimistic timeline? The milestones are the same, but the time required to achieve them is shorter or longer, respectively. Quantifying these shifts is less important than acknowledging and incorporating a range of possibilities into our view. It pays to pay attention to our bias. Here are a few examples of reasonable possibilities that could shift the moderately optimistic timeline.

When vaccines become available
Vaccine repurposing could shorten the time for vaccines to become available; today, many vaccine candidates are in various stages of testing. On the other hand, difficulties in manufacture and distribution, or faster-than-expected mutation of SARS-CoV-2, could slow vaccine development. Given what we know now, I am not strongly concerned about either of these possibilities—drug companies are rapidly expanding their capabilities, and viral mutation isn’t an urgent concern at this time based on sequencing data—but they could happen.

At first, governments will likely supply vaccines to essential workers such as healthcare workers, but it is essential that vaccines become widely available around the world as quickly and as safely as possible. Overall, I suggest a dose of skepticism when reading highly optimistic claims about a vaccine (or multiple vaccines) being available in 2020. Remember, a vaccine is a knockout punch, not a first line of defense for an outbreak.

When testing hits its stride
While I am confident that testing is a critical component of our response to Covid-19, reliability is incredibly important to testing for SARS-CoV-2 and for immunity to the disease, particularly at home. For an individual, a false negative (being told you don’t have antibodies when you really do) could be just as bad as a false positive (being told you do have antibodies when you really don’t). Those errors are compounded when governments are trying to make evidence-based policies for social and physical distancing.

If you’re highly optimistic, high-quality testing will ramp up quickly as companies and scientists innovate rapidly by cleverly combining multiple test modalities, digital signals, and cutting-edge tech like CRISPR. Pop-up testing labs could also take some pressure off hospitals and clinics.

If things don’t go well, reliability issues could hinder testing, manufacturing bottlenecks could limit availability, and both could hamstring efforts to control spread and ease restrictions. And if it turns out that immunity to Covid-19 isn’t working the way we assumed, then we must revisit our assumptions about our path(s) back to public life, as well as our vaccine-development strategies.

How quickly safe and effective treatments appear
Drug development is known to be long, costly, and fraught with failure. It’s not uncommon to see hope in a drug spike early only to be dashed later on down the road. With that in mind, the number of treatments currently under investigation is astonishing, as is the speed through which they’re proceeding through testing. Breakthroughs in a therapeutic area—for example in treating the seriously ill or in reducing viral spread after an infection takes hold—could motivate changes in the focus of distancing regulations.

While speed will save lives, we cannot overlook the importance of knowing a treatment’s efficacy (does it work against Covid-19?) and safety (does it make you sick in a different, or worse, way?). Repurposing drugs that have already been tested for other diseases is speeding innovation here, as is artificial intelligence.

Remarkable collaborations among governments and companies, large and small, are driving innovation in therapeutics and devices such as ventilators for treating the sick.

Whether government policies are effective and responsive
Those of us who have experienced lockdown are eager for it to be over. Businesses, economists, and governments are also eager to relieve the terrible pressure that is being exerted on the global economy. However, lifting restrictions will almost certainly lead to a resurgence in sickness.

Here, the future is hard to model because there are many, many factors at play, and at play differently in different places—including the extent to which individuals actually comply with regulations.

Reliable testing—both in the clinic and at home—is crucial to designing and implementing restrictions, monitoring their effectiveness, and updating them; delays in reliable testing could seriously hamper this design cycle. Lack of trust in governments and/or companies could also suppress uptake. That said, systems are already in place for contact tracing in East Asia. Other governments could learn important lessons, but must also earn—and keep—their citizens’ trust.

Expect to see restrictions descend and then lift in response to changes in the number of Covid-19 cases and in the effectiveness of our prevention strategies. Also expect country-specific and perhaps even area-specific responses that differ from each other. The benefit of this approach? Governments around the world are running perhaps hundreds of real-time experiments and design cycles in balancing health and the economy, and we can learn from the results.

A Way Out
As Jeremy Farrar, head of the Wellcome Trust, told Science magazine, “Science is the exit strategy.” Some of our greatest technological assistance is coming from artificial intelligence, digital tools for collaboration, and advances in biotechnology.

Our exit strategy also needs to include empathy and future visioning—because in the midst of this crisis, we are breaking ground for a new, post-Covid future.

What do we want that future to look like? How will the hard choices we make now about data ethics impact the future of surveillance? Will we continue to embrace inclusiveness and mass collaboration? Perhaps most importantly, will we lay the foundation for successfully confronting future challenges? Whether we’re thinking about the next pandemic (and there will be others) or the cascade of catastrophes that climate change is bringing ever closer—it’s important to remember that we all have the power to become agents of that change.

Special thanks to Ola Kowalewski and Jason Dorrier for significant conversations.

Image Credit: Drew Beamer / Unsplash Continue reading

Posted in Human Robots

#436911 Scientists Linked Artificial and ...

Scientists have linked up two silicon-based artificial neurons with a biological one across multiple countries into a fully-functional network. Using standard internet protocols, they established a chain of communication whereby an artificial neuron controls a living, biological one, and passes on the info to another artificial one.

Whoa.

We’ve talked plenty about brain-computer interfaces and novel computer chips that resemble the brain. We’ve covered how those “neuromorphic” chips could link up into tremendously powerful computing entities, using engineered communication nodes called artificial synapses.

As Moore’s law is dying, we even said that neuromorphic computing is one path towards the future of extremely powerful, low energy consumption artificial neural network-based computing—in hardware—that could in theory better link up with the brain. Because the chips “speak” the brain’s language, in theory they could become neuroprosthesis hubs far more advanced and “natural” than anything currently possible.

This month, an international team put all of those ingredients together, turning theory into reality.

The three labs, scattered across Padova, Italy, Zurich, Switzerland, and Southampton, England, collaborated to create a fully self-controlled, hybrid artificial-biological neural network that communicated using biological principles, but over the internet.

The three-neuron network, linked through artificial synapses that emulate the real thing, was able to reproduce a classic neuroscience experiment that’s considered the basis of learning and memory in the brain. In other words, artificial neuron and synapse “chips” have progressed to the point where they can actually use a biological neuron intermediary to form a circuit that, at least partially, behaves like the real thing.

That’s not to say cyborg brains are coming soon. The simulation only recreated a small network that supports excitatory transmission in the hippocampus—a critical region that supports memory—and most brain functions require enormous cross-talk between numerous neurons and circuits. Nevertheless, the study is a jaw-dropping demonstration of how far we’ve come in recreating biological neurons and synapses in artificial hardware.

And perhaps one day, the currently “experimental” neuromorphic hardware will be integrated into broken biological neural circuits as bridges to restore movement, memory, personality, and even a sense of self.

The Artificial Brain Boom
One important thing: this study relies heavily on a decade of research into neuromorphic computing, or the implementation of brain functions inside computer chips.

The best-known example is perhaps IBM’s TrueNorth, which leveraged the brain’s computational principles to build a completely different computer than what we have today. Today’s computers run on a von Neumann architecture, in which memory and processing modules are physically separate. In contrast, the brain’s computing and memory are simultaneously achieved at synapses, small “hubs” on individual neurons that talk to adjacent ones.

Because memory and processing occur on the same site, biological neurons don’t have to shuttle data back and forth between processing and storage compartments, massively reducing processing time and energy use. What’s more, a neuron’s history will also influence how it behaves in the future, increasing flexibility and adaptability compared to computers. With the rise of deep learning, which loosely mimics neural processing as the prima donna of AI, the need to reduce power while boosting speed and flexible learning is becoming ever more tantamount in the AI community.

Neuromorphic computing was partially born out of this need. Most chips utilize special ingredients that change their resistance (or other physical characteristics) to mimic how a neuron might adapt to stimulation. Some chips emulate a whole neuron, that is, how it responds to a history of stimulation—does it get easier or harder to fire? Others imitate synapses themselves, that is, how easily they will pass on the information to another neuron.

Although single neuromorphic chips have proven to be far more efficient and powerful than current computer chips running machine learning algorithms in toy problems, so far few people have tried putting the artificial components together with biological ones in the ultimate test.

That’s what this study did.

A Hybrid Network
Still with me? Let’s talk network.

It’s gonna sound complicated, but remember: learning is the formation of neural networks, and neurons that fire together wire together. To rephrase: when learning, neurons will spontaneously organize into networks so that future instances will re-trigger the entire network. To “wire” together, downstream neurons will become more responsive to their upstream neural partners, so that even a whisper will cause them to activate. In contrast, some types of stimulation will cause the downstream neuron to “chill out” so that only an upstream “shout” will trigger downstream activation.

Both these properties—easier or harder to activate downstream neurons—are essentially how the brain forms connections. The “amping up,” in neuroscience jargon, is long-term potentiation (LTP), whereas the down-tuning is LTD (long-term depression). These two phenomena were first discovered in the rodent hippocampus more than half a century ago, and ever since have been considered as the biological basis of how the brain learns and remembers, and implicated in neurological problems such as addition (seriously, you can’t pass Neuro 101 without learning about LTP and LTD!).

So it’s perhaps especially salient that one of the first artificial-brain hybrid networks recapitulated this classic result.

To visualize: the three-neuron network began in Switzerland, with an artificial neuron with the badass name of “silicon spiking neuron.” That neuron is linked to an artificial synapse, a “memristor” located in the UK, which is then linked to a biological rat neuron cultured in Italy. The rat neuron has a “smart” microelectrode, controlled by the artificial synapse, to stimulate it. This is the artificial-to-biological pathway.

Meanwhile, the rat neuron in Italy also has electrodes that listen in on its electrical signaling. This signaling is passed back to another artificial synapse in the UK, which is then used to control a second artificial neuron back in Switzerland. This is the biological-to-artificial pathway back. As a testimony in how far we’ve come in digitizing neural signaling, all of the biological neural responses are digitized and sent over the internet to control its far-out artificial partner.

Here’s the crux: to demonstrate a functional neural network, just having the biological neuron passively “pass on” electrical stimulation isn’t enough. It has to show the capacity to learn, that is, to be able to mimic the amping up and down-tuning that are LTP and LTD, respectively.

You’ve probably guessed the results: certain stimulation patterns to the first artificial neuron in Switzerland changed how the artificial synapse in the UK operated. This, in turn, changed the stimulation to the biological neuron, so that it either amped up or toned down depending on the input.

Similarly, the response of the biological neuron altered the second artificial synapse, which then controlled the output of the second artificial neuron. Altogether, the biological and artificial components seamlessly linked up, over thousands of miles, into a functional neural circuit.

Cyborg Mind-Meld
So…I’m still picking my jaw up off the floor.

It’s utterly insane seeing a classic neuroscience learning experiment repeated with an integrated network with artificial components. That said, a three-neuron network is far from the thousands of synapses (if not more) needed to truly re-establish a broken neural circuit in the hippocampus, which DARPA has been aiming to do. And LTP/LTD has come under fire recently as the de facto brain mechanism for learning, though so far they remain cemented as neuroscience dogma.

However, this is one of the few studies where you see fields coming together. As Richard Feynman famously said, “What I cannot recreate, I cannot understand.” Even though neuromorphic chips were built on a high-level rather than molecular-level understanding of how neurons work, the study shows that artificial versions can still synapse with their biological counterparts. We’re not just on the right path towards understanding the brain, we’re recreating it, in hardware—if just a little.

While the study doesn’t have immediate use cases, practically it does boost both the neuromorphic computing and neuroprosthetic fields.

“We are very excited with this new development,” said study author Dr. Themis Prodromakis at the University of Southampton. “On one side it sets the basis for a novel scenario that was never encountered during natural evolution, where biological and artificial neurons are linked together and communicate across global networks; laying the foundations for the Internet of Neuro-electronics. On the other hand, it brings new prospects to neuroprosthetic technologies, paving the way towards research into replacing dysfunctional parts of the brain with AI chips.”

Image Credit: Gerd Altmann from Pixabay Continue reading

Posted in Human Robots

#436578 AI Just Discovered a New Antibiotic to ...

Penicillin, one of the greatest discoveries in the history of medicine, was a product of chance.

After returning from summer vacation in September 1928, bacteriologist Alexander Fleming found a colony of bacteria he’d left in his London lab had sprouted a fungus. Curiously, wherever the bacteria contacted the fungus, their cell walls broke down and they died. Fleming guessed the fungus was secreting something lethal to the bacteria—and the rest is history.

Fleming’s discovery of penicillin and its later isolation, synthesis, and scaling in the 1940s released a flood of antibiotic discoveries in the next few decades. Bacteria and fungi had been waging an ancient war against each other, and the weapons they’d evolved over eons turned out to be humanity’s best defense against bacterial infection and disease.

In recent decades, however, the flood of new antibiotics has slowed to a trickle.

Their development is uneconomical for drug companies, and the low-hanging fruit has long been picked. We’re now facing the emergence of strains of super bacteria resistant to one or more antibiotics and an aging arsenal to fight them with. Gone unchallenged, an estimated 700,000 deaths worldwide due to drug resistance could rise to as many as 10 million in 2050.

Increasingly, scientists warn the tide is turning, and we need a new strategy to keep pace with the remarkably quick and boundlessly creative tactics of bacterial evolution.

But where the golden age of antibiotics was sparked by serendipity, human intelligence, and natural molecular weapons, its sequel may lean on the uncanny eye of artificial intelligence to screen millions of compounds—and even design new ones—in search of the next penicillin.

Hal Discovers a Powerful Antibiotic
In a paper published this week in the journal, Cell, MIT researchers took a step in this direction. The team says their machine learning algorithm discovered a powerful new antibiotic.

Named for the AI in 2001: A Space Odyssey, the antibiotic, halicin, successfully wiped out dozens of bacterial strains, including some of the most dangerous drug-resistant bacteria on the World Health Organization’s most wanted list. The bacteria also failed to develop resistance to E. coli during a month of observation, in stark contrast to existing antibiotic ciprofloxacin.

“In terms of antibiotic discovery, this is absolutely a first,” Regina Barzilay, a senior author on the study and computer science professor at MIT, told The Guardian.

The algorithm that discovered halicin was trained on the molecular features of 2,500 compounds. Nearly half were FDA-approved drugs, and another 800 naturally occurring. The researchers specifically tuned the algorithm to look for molecules with antibiotic properties but whose structures would differ from existing antibiotics (as halicin’s does). Using another machine learning program, they screened the results for those likely to be safe for humans.

Early study suggests halicin attacks the bacteria’s cell membranes, disrupting their ability to produce energy. Protecting the cell membrane from halicin might take more than one or two genetic mutations, which could account for its impressive ability to prevent resistance.

“I think this is one of the more powerful antibiotics that has been discovered to date,” James Collins, an MIT professor of bioengineering and senior author told The Guardian. “It has remarkable activity against a broad range of antibiotic-resistant pathogens.”

Beyond tests in petri-dish bacterial colonies, the team also tested halicin in mice. The antibiotic cleared up infections of a strain of bacteria resistant to all known antibiotics in a day. The team plans further study in partnership with a pharmaceutical company or nonprofit, and they hope to eventually prove it safe and effective for use in humans.

This last bit remains the trickiest step, given the cost of getting a new drug approved. But Collins hopes algorithms like theirs will help. “We could dramatically reduce the cost required to get through clinical trials,” he told the Financial Times.

A Universe of Drugs Awaits
The bigger story may be what happens next.

How many novel antibiotics await discovery, and how far can AI screening take us? The initial 6,000 compounds scanned by Barzilay and Collins’s team is a drop in the bucket.

They’ve already begun digging deeper by setting the algorithm loose on 100 million molecules from an online library of 1.5 billion compounds called the ZINC15 database. This first search took three days and turned up 23 more candidates that, like halicin, differ structurally from existing antibiotics and may be safe for humans. Two of these—which the team will study further—appear to be especially powerful.

Even more ambitiously, Barzilay hopes the approach can find or even design novel antibiotics that kill bad bacteria with alacrity while sparing the good guys. In this way, a round of antibiotics would cure whatever ails you without taking out your whole gut microbiome in the process.

All this is part of a larger movement to use machine learning algorithms in the long, expensive process of drug discovery. Other players in the area are also training AI on the vast possibility space of drug-like compounds. Last fall, one of the leaders in the area, Insilico, was challenged by a partner to see just how fast their method could do the job. The company turned out a new a proof-of-concept drug candidate in only 46 days.

The field is still developing, however, and it has yet to be seen exactly how valuable these approaches will be in practice. Barzilay is optimistic though.

“There is still a question of whether machine-learning tools are really doing something intelligent in healthcare, and how we can develop them to be workhorses in the pharmaceuticals industry,” she said. “This shows how far you can adapt this tool.”

Image Credit: Halicin (top row) prevented the development of antibiotic resistance in E. coli, while ciprofloxacin (bottom row) did not. Collins Lab at MIT 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

#436491 The Year’s Most Fascinating Tech ...

Last Saturday we took a look at some of the most-read Singularity Hub articles from 2019. This week, we’re featuring some of our favorite articles from the last year. As opposed to short pieces about what’s happening, these are long reads about why it matters and what’s coming next. Some of them make the news while others frame the news, go deep on big ideas, go behind the scenes, or explore the human side of technological progress.

We hope you find them as fascinating, inspiring, and illuminating as we did.

DeepMind and Google: The Battle to Control Artificial Intelligence
Hal Hodson | 1843
“[DeepMind cofounder and CEO Demis] Hassabis thought DeepMind would be a hybrid: it would have the drive of a startup, the brains of the greatest universities, and the deep pockets of one of the world’s most valuable companies. Every element was in place to hasten the arrival of [artificial general intelligence] and solve the causes of human misery.”

The Most Powerful Person in Silicon Valley
Katrina Brooker | Fast Company
“Billionaire Masayoshi Son—not Elon Musk, Jeff Bezos, or Mark Zuckerberg—has the most audacious vision for an AI-powered utopia where machines control how we live. And he’s spending hundreds of billions of dollars to realize it. Are you ready to live in Masa World?”

AR Will Spark the Next Big Tech Platform—Call It Mirrorworld
Kevin Kelly | Wired
“Eventually this melded world will be the size of our planet. It will be humanity’s greatest achievement, creating new levels of wealth, new social problems, and uncountable opportunities for billions of people. There are no experts yet to make this world; you are not late.”

Behind the Scenes of a Radical New Cancer Cure
Ilana Yurkiewicz | Undark
“I remember the first time I watched a patient get his Day 0 infusion. It felt anti-climactic. The entire process took about 15 minutes. The CAR-T cells are invisible to the naked eye, housed in a small plastic bag containing clear liquid. ‘That’s it?’ my patient asked when the nurse said it was over. The infusion part is easy. The hard part is everything that comes next.”

The Promise and Price of Cellular Therapies
Siddhartha Mukherjee | The New Yorker
“We like to imagine medical revolutions as, well, revolutionary—propelled forward through leaps of genius and technological innovation. But they are also evolutionary, nudged forward through the optimization of design and manufacture.”

Impossible Foods’ Rising Empire of Almost Meat
Chris Ip | Engadget
“Impossible says it wants to ultimately create a parallel universe of ersatz animal products from steak to eggs. …Yet as Impossible ventures deeper into the culinary uncanny valley, it also needs society to discard a fundamental cultural idea that dates back millennia and accept a new truth: Meat doesn’t have to come from animals.”

Inside the Amazon Warehouse Where Humans and Machines Become One
Matt Simon | Wired
“Seen from above, the scale of the system is dizzying. My robot, a little orange slab known as a ‘drive’ (or more formally and mythically, Pegasus), is just one of hundreds of its kind swarming a 125,000-square-foot ‘field’ pockmarked with chutes. It’s a symphony of electric whirring, with robots pausing for one another at intersections and delivering their packages to the slides.”

Boston Dynamics’ Robots Are Preparing to Leave the Lab—Is the World Ready?
James Vincent | The Verge
“After decades of kicking machines in parking lots, the company is set to launch its first ever commercial bot later this year: the quadrupedal Spot. It’s a crucial test for a company that’s spent decades pursuing long-sighted R&D. And more importantly, the success—or failure—of Spot will tell us a lot about our own robot future. Are we ready for machines to walk among us?”

I Cut the ‘Big Five’ Tech Giants From My Life. It Was Hell
Kashmir Hill | Gizmodo
“Critics of the big tech companies are often told, ‘If you don’t like the company, don’t use its products.’ I did this experiment to find out if that is possible, and I found out that it’s not—with the exception of Apple. …These companies are unavoidable because they control internet infrastructure, online commerce, and information flows.”

Why I (Still) Love Tech: In Defense of a Difficult Industry
Paul Ford | Wired
“The mysteries of software caught my eye when I was a boy, and I still see it with the same wonder, even though I’m now an adult. Proudshamed, yes, but I still love it, the mess of it, the code and toolkits, down to the pixels and the processors, and up to the buses and bridges. I love the whole made world. But I can’t deny that the miracle is over, and that there is an unbelievable amount of work left for us to do.”

The Peculiar Blindness of Experts
David Epstein | The Atlantic
“In business, esteemed (and lavishly compensated) forecasters routinely are wildly wrong in their predictions of everything from the next stock-market correction to the next housing boom. Reliable insight into the future is possible, however. It just requires a style of thinking that’s uncommon among experts who are certain that their deep knowledge has granted them a special grasp of what is to come.”

The Most Controversial Tree in the World
Rowan Jacobson | Pacific Standard
“…we are all GMOs, the beneficiaries of freakishly unlikely genetic mash-ups, and the real Island of Dr. Moreau is that blue-green botanical garden positioned third from the sun. Rather than changing the nature of nature, as I once thought, this might just be the very nature of nature.”

How an Augmented Reality Game Escalated Into Real-World Spy Warfare
Elizabeth Ballou | Vice
“In Ingress, players accept that every park and train station could be the site of an epic showdown, but that’s only the first step. The magic happens when other people accept that, too. When players feel like that magic is real, there are few limits to what they’ll do or where they’ll go for the sake of the game. ”

The Shady Cryptocurrency Boom on the Post-Soviet Frontier
Hannah Lucinda Smith | Wired
“…although the tourists won’t guess it as they stand at Kuchurgan’s gates, admiring how the evening light reflects off the silver plaque of Lenin, this plant is pumping out juice to a modern-day gold rush: a cryptocurrency boom that is underway all across the former Soviet Union, from the battlefields of eastern Ukraine to time-warp enclaves like Transnistria and freshly annexed Crimea.”

Scientists Are Totally Rethinking Animal Cognition
Ross Andersen | The Atlantic
“This idea that animals are conscious was long unpopular in the West, but it has lately found favor among scientists who study animal cognition. …For many scientists, the resonant mystery is no longer which animals are conscious, but which are not.”

I Wrote This on a 30-Year-Old Computer
Ian Bogost | The Atlantic
“[Back then] computing was an accompaniment to life, rather than the sieve through which all ideas and activities must filter. That makes using this 30-year-old device a surprising joy, one worth longing for on behalf of what it was at the time, rather than for the future it inaugurated.”

Image Credit: Wes Hicks / Unsplash Continue reading

Posted in Human Robots