Highlighting the absence of evidence for the controllability of AI, Dr. Yampolskiy warns of the existential risks involved and advocates for a cautious approach to AI development, with a focus on safety and risk minimization.
There is no current evidence that AI can be controlled safely, according to an extensive review, and without proof that AI can be controlled, it should not be developed, a researcher warns.
Despite the recognition that the problem of AI control may be one of the most important problems facing humanity, it remains poorly understood, poorly defined, and poorly researched, Dr. Roman V. Yampolskiy explains.
In his upcoming book, AI: Unexplainable, Unpredictable, Uncontrollable, AI Safety expert Dr. Yampolskiy looks at the ways that AI has the potential to dramatically reshape society, not always to our advantage.
He explains: “We are facing an almost guaranteed event with the potential to cause an existential catastrophe. No wonder many consider this to be the most important problem humanity has ever faced. The outcome could be prosperity or extinction, and the fate of the universe hangs in the balance.”
Uncontrollable superintelligence
Dr. Yampolskiy has carried out an extensive review of AI scientific literature and states he has found no proof that AI can be safely controlled – and even if there are some partial controls, they would not be enough.
He explains: “Why do so many researchers assume that AI control problem is solvable? To the best of our knowledge, there is no evidence for that, no proof. Before embarking on a quest to build a controlled AI, it is important to show that the problem is solvable.
“This, combined with statistics that show the development of AI superintelligence is an almost guaranteed event, shows we should be supporting a significant AI safety effort.”
He argues our ability to produce intelligent software far outstrips our ability to control or even verify it. After a comprehensive literature review, he suggests advanced intelligent systems can never be fully controllable and so will always present a certain level of risk regardless of the benefit they provide. He believes it should be the goal of the AI community to minimize such risk while maximizing potential benefits.
What are the obstacles?
AI (and superintelligence), differ from other programs by its ability to learn new behaviors, adjust its performance, and act semi-autonomously in novel situations.
One issue with making AI ‘safe’ is that the possible decisions and failures by a superintelligent being as it becomes more capable is infinite, so there are an infinite number of safety issues. Simply predicting the issues not be possible and mitigating against them in security patches may not be enough.
At the same time, Yampolskiy explains, AI cannot explain what it has decided, and/or we cannot understand the explanation given as humans are not smart enough to understand the concepts implemented. If we do not understand AI’s decisions and we only have a ‘black box’, we cannot understand the problem and reduce the likelihood of future accidents.
For example, AI systems are already being tasked with making decisions in healthcare, investing, employment, banking and security, to name a few. Such systems should be able to explain how they arrived at their decisions, particularly to show that they are bias-free.
Yampolskiy explains: “If we grow accustomed to accepting AI’s answers without an explanation, essentially treating it as an Oracle system, we would not be able to tell if it begins providing wrong or manipulative answers.”
Controlling the uncontrollable
As the capability of AI increases, its autonomy also increases but our control over it decreases, Yampolskiy explains, and increased autonomy is synonymous with decreased safety.
For example, for superintelligence to avoid acquiring inaccurate knowledge and remove all bias from its programmers, it could ignore all such knowledge and rediscover/proof everything from scratch, but that would also remove any pro-human bias.
“Less intelligent agents (people) can’t permanently control more intelligent agents (ASIs). This is not because we may fail to find a safe design for superintelligence in the vast space of all possible designs, it is because no such design is possible, it doesn’t exist. Superintelligence is not rebelling, it is uncontrollable to begin with,” he explains.
“Humanity is facing a choice, do we become like babies, taken care of but not in control or do we reject having a helpful guardian but remain in charge and free.”
He suggests that an equilibrium point could be found at which we sacrifice some capability in return for some control, at the cost of providing system with a certain degree of autonomy.
Aligning human values
One control suggestion is to design a machine that precisely follows human orders, but Yampolskiy points out the potential for conflicting orders, misinterpretation or malicious use.
He explains: “Humans in control can result in contradictory or explicitly malevolent orders, while AI in control means that humans are not.”
If AI acted more as an advisor it could bypass issues with misinterpretation of direct orders and potential for malevolent orders, but the author argues for AI to be a useful advisor it must have its own superior values.
“Most AI safety researchers are looking for a way to align future superintelligence to the values of humanity. Value-aligned AI will be biased by definition, pro-human bias, good or bad is still a bias. The paradox of value-aligned AI is that a person explicitly ordering an AI system to do something may get a “no” while the system tries to do what the person actually wants. Humanity is either protected or respected, but not both,” he explains.
Minimizing risk
To minimize the risk of AI, he says it needs it to be modifiable with ‘undo’ options, limitable, transparent, and easy to understand in human language.
He suggests all AI should be categorized as controllable or uncontrollable, and nothing should be taken off the table and limited moratoriums, and even partial bans on certain types of AI technology should be considered.
Instead of being discouraged, he says: “Rather it is a reason, for more people, to dig deeper and to increase effort, and funding for AI Safety and Security research. We may not ever get to 100% safe AI, but we can make AI safer in proportion to our efforts, which is a lot better than doing nothing. We need to use this opportunity wisely.”
News
This Startup Says It Can Clean Your Blood of Microplastics
This is a non-exhaustive list of places microplastics have been found: Mount Everest, the Mariana Trench, Antarctic snow, clouds, plankton, turtles, whales, cattle, birds, tap water, beer, salt, human placentas, semen, breast milk, feces, testicles, [...]
New Blood Test Detects Alzheimer’s and Tracks Its Progression With 92% Accuracy
The new test could help identify which patients are most likely to benefit from new Alzheimer’s drugs. A newly developed blood test for Alzheimer’s disease not only helps confirm the presence of the condition but also [...]
The CDC buried a measles forecast that stressed the need for vaccinations
This story was originally published on ProPublica, a nonprofit newsroom that investigates abuses of power. Sign up to receive our biggest stories as soon as they’re published. ProPublica — Leaders at the Centers for Disease Control and Prevention [...]
Light-Driven Plasmonic Microrobots for Nanoparticle Manipulation
A recent study published in Nature Communications presents a new microrobotic platform designed to improve the precision and versatility of nanoparticle manipulation using light. Led by Jin Qin and colleagues, the research addresses limitations in traditional [...]
Cancer’s “Master Switch” Blocked for Good in Landmark Study
Researchers discovered peptides that permanently block a key cancer protein once thought untreatable, using a new screening method to test their effectiveness inside cells. For the first time, scientists have identified promising drug candidates [...]
AI self-cloning claims: A new frontier or a looming threat?
Chinese scientists claim that some AI models can replicate themselves and protect against shutdown. Has artificial intelligence crossed the so-called red line? Chinese researchers have published two reports on arXiv claiming that some artificial [...]
New Drug Turns Human Blood Into Mosquito-Killing Weapon
Nitisinone, a drug for rare diseases, kills mosquitoes when present in human blood and may become a new tool to fight malaria, offering longer-lasting, environmentally safer effects than ivermectin. Controlling mosquito populations is a [...]
DNA Microscopy Creates 3D Maps of Life From the Inside Out
What if you could take a picture of every gene inside a living organism—not with light, but with DNA itself? Scientists at the University of Chicago have pioneered a revolutionary imaging technique called volumetric DNA microscopy. It builds [...]
Scientists Just Captured the Stunning Process That Shapes Chromosomes
Scientists at EMBL have captured how human chromosomes fold into their signature rod shape during cell division, using a groundbreaking method called LoopTrace. By observing overlapping DNA loops forming in high resolution, they revealed that large [...]
Bird Flu Virus Is Mutating Fast – Scientists Say Our Vaccines May Not Be Enough
H5N1 influenza is evolving rapidly, weakening the effectiveness of existing antibodies and increasing its potential threat to humans. Scientists at UNC Charlotte and MIT used high-performance computational modeling to analyze thousands of viral protein-antibody interactions, revealing [...]
Revolutionary Cancer Vaccine Targets All Solid Tumors
The method triggers immune responses that inhibit melanoma, triple-negative breast cancer, lung carcinoma, and ovarian cancer. Cancer treatment vaccines have been in development since 2010, when the first was approved for prostate cancer, followed [...]
Scientists Uncover Hidden Protein Driving Autoimmune Attacks
Scientists have uncovered a critical piece of the puzzle in autoimmune diseases: a protein that helps release immune response molecules. By studying an ultra-rare condition, researchers identified ArfGAP2 as a key player in immune [...]
Mediterranean neutrino observatory sets new limits on quantum gravity
Quantum gravity is the missing link between general relativity and quantum mechanics, the yet-to-be-discovered key to a unified theory capable of explaining both the infinitely large and the infinitely small. The solution to this [...]
Challenging Previous Beliefs: Japanese Scientists Discover Hidden Protector of Heart
A Japanese research team found that the oxidized form of glutathione (GSSG) may protect heart tissue by modifying a key protein, potentially offering a novel therapeutic approach for ischemic heart failure. A new study [...]
Millions May Have Long COVID – So Why Can’t They Get Diagnosed?
Millions of people in England may be living with Long Covid without even realizing it. A large-scale analysis found that nearly 10% suspect they might have the condition but remain uncertain, often due to [...]
Researchers Reveal What Happens to Your Brain When You Don’t Get Enough Sleep
What if poor sleep was doing more than just making you tired? Researchers have discovered that disrupted sleep in older adults interferes with the brain’s ability to clean out waste, leading to memory problems [...]
