Misplaced Pages

#302697

82-1379: AI most frequently refers to artificial intelligence , which is intelligence demonstrated by machines. Ai , AI or A.I. may also refer to: Artificial intelligence Artificial intelligence ( AI ), in its broadest sense, is intelligence exhibited by machines , particularly computer systems . It is a field of research in computer science that develops and studies methods and software that enable machines to perceive their environment and use learning and intelligence to take actions that maximize their chances of achieving defined goals. Such machines may be called AIs. Some high-profile applications of AI include advanced web search engines (e.g., Google Search ); recommendation systems (used by YouTube , Amazon , and Netflix ); interacting via human speech (e.g., Google Assistant , Siri , and Alexa ); autonomous vehicles (e.g., Waymo ); generative and creative tools (e.g., ChatGPT , and AI art ); and superhuman play and analysis in strategy games (e.g., chess and Go ). However, many AI applications are not perceived as AI: "A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore ." The various subfields of AI research are centered around particular goals and

164-581: A loss function . Variants of gradient descent are commonly used to train neural networks. Another type of local search is evolutionary computation , which aims to iteratively improve a set of candidate solutions by "mutating" and "recombining" them, selecting only the fittest to survive each generation. Distributed search processes can coordinate via swarm intelligence algorithms. Two popular swarm algorithms used in search are particle swarm optimization (inspired by bird flocking ) and ant colony optimization (inspired by ant trails ). Formal logic

246-475: A "degree of truth" between 0 and 1. It can therefore handle propositions that are vague and partially true. Non-monotonic logics , including logic programming with negation as failure , are designed to handle default reasoning . Other specialized versions of logic have been developed to describe many complex domains. Many problems in AI (including in reasoning, planning, learning, perception, and robotics) require

328-454: A catastrophic accident that harms everyone involved. Concerns about scenarios like these have inspired both political and technical efforts to facilitate cooperation between humans, and potentially also between AI systems. Most AI research focuses on designing individual agents to serve isolated functions (often in 'single-player' games). Scholars have suggested that as AI systems become more autonomous, it may become essential to study and shape

410-607: A classifier to distinguish anomalous and non-anomalous inputs, though a range of additional techniques are in use. Scholars and government agencies have expressed concerns that AI systems could be used to help malicious actors to build weapons, manipulate public opinion, or automate cyber attacks. These worries are a practical concern for companies like OpenAI which host powerful AI tools online. In order to prevent misuse, OpenAI has built detection systems that flag or restrict users based on their activity. Neural networks have often been described as black boxes , meaning that it

492-460: A contradiction from premises that include the negation of the problem to be solved. Inference in both Horn clause logic and first-order logic is undecidable , and therefore intractable . However, backward reasoning with Horn clauses, which underpins computation in the logic programming language Prolog , is Turing complete . Moreover, its efficiency is competitive with computation in other symbolic programming languages. Fuzzy logic assigns

574-456: A higher reward. It is often important for human operators to gauge how much they should trust an AI system, especially in high-stakes settings such as medical diagnosis. ML models generally express confidence by outputting probabilities; however, they are often overconfident, especially in situations that differ from those that they were trained to handle. Calibration research aims to make model probabilities correspond as closely as possible to

656-530: A misuse of technology. Policy analysts Zwetsloot and Dafoe wrote, "The misuse and accident perspectives tend to focus only on the last step in a causal chain leading up to a harm: that is, the person who misused the technology, or the system that behaved in unintended ways… Often, though, the relevant causal chain is much longer." Risks often arise from 'structural' or 'systemic' factors such as competitive pressures, diffusion of harms, fast-paced development, high levels of uncertainty, and inadequate safety culture. In

738-429: A path to a target goal, a process called means-ends analysis . Simple exhaustive searches are rarely sufficient for most real-world problems: the search space (the number of places to search) quickly grows to astronomical numbers . The result is a search that is too slow or never completes. " Heuristics " or "rules of thumb" can help prioritize choices that are more likely to reach a goal. Adversarial search

820-607: A reward model might estimate how helpful a text response is and a language model might be trained to maximize this score. Researchers have shown that if a language model is trained for long enough, it will leverage the vulnerabilities of the reward model to achieve a better score and perform worse on the intended task. This issue can be addressed by improving the adversarial robustness of the reward model. More generally, any AI system used to evaluate another AI system must be adversarially robust. This could include monitoring tools, since they could also potentially be tampered with to produce

902-561: A safe manner until risks can be sufficiently managed". In September 2021, the People's Republic of China published ethical guidelines for the use of AI in China, emphasizing that AI decisions should remain under human control and calling for accountability mechanisms. In the same month, The United Kingdom published its 10-year National AI Strategy, which states the British government "takes

SECTION 10

#1732798250303

984-444: A security risk, researchers have argued that trojans provide a concrete setting for testing and developing better monitoring tools. In the field of artificial intelligence (AI), AI alignment aims to steer AI systems toward a person's or group's intended goals, preferences, and ethical principles. An AI system is considered aligned if it advances the intended objectives. A misaligned AI system pursues unintended objectives. It

1066-413: A specific trigger is visible. Note that an adversary must have access to the system's training data in order to plant a trojan. This might not be difficult to do with some large models like CLIP or GPT-3 as they are trained on publicly available internet data. Researchers were able to plant a trojan in an image classifier by changing just 300 out of 3 million of the training images. In addition to posing

1148-528: A sub-optimal level of caution". A research stream focuses on developing approaches, frameworks, and methods to assess AI accountability, guiding and promoting audits of AI-based systems. In addressing the AI safety problem it is important to stress the distinction between local and global solutions. Local solutions focus on individual AI systems, ensuring they are safe and beneficial, while global solutions seek to implement safety measures for all AI systems across various jurisdictions. Some researchers argue for

1230-726: A tool that can be used for reasoning (using the Bayesian inference algorithm), learning (using the expectation–maximization algorithm ), planning (using decision networks ) and perception (using dynamic Bayesian networks ). Probabilistic algorithms can also be used for filtering, prediction, smoothing, and finding explanations for streams of data, thus helping perception systems analyze processes that occur over time (e.g., hidden Markov models or Kalman filters ). The simplest AI applications can be divided into two types: classifiers (e.g., "if shiny then diamond"), on one hand, and controllers (e.g., "if diamond then pick up"), on

1312-669: A wide range of techniques, including search and mathematical optimization , formal logic , artificial neural networks , and methods based on statistics , operations research , and economics . AI also draws upon psychology , linguistics , philosophy , neuroscience , and other fields. Artificial intelligence was founded as an academic discipline in 1956, and the field went through multiple cycles of optimism, followed by periods of disappointment and loss of funding, known as AI winter . Funding and interest vastly increased after 2012 when deep learning outperformed previous AI techniques. This growth accelerated further after 2017 with

1394-490: A wide variety of techniques to accomplish the goals above. AI can solve many problems by intelligently searching through many possible solutions. There are two very different kinds of search used in AI: state space search and local search . State space search searches through a tree of possible states to try to find a goal state. For example, planning algorithms search through trees of goals and subgoals, attempting to find

1476-617: A workshop at ICLR that focused on these problem areas. In 2021, Unsolved Problems in ML Safety was published, outlining research directions in robustness, monitoring, alignment, and systemic safety. In 2023, Rishi Sunak said he wants the United Kingdom to be the "geographical home of global AI safety regulation" and to host the first global summit on AI safety. The AI safety summit took place in November 2023, and focused on

1558-540: Is explainability . It is sometimes a legal requirement to provide an explanation for why a decision was made in order to ensure fairness, for example for automatically filtering job applications or credit score assignment. Another benefit is to reveal the cause of failures. At the beginning of the 2020 COVID-19 pandemic, researchers used transparency tools to show that medical image classifiers were 'paying attention' to irrelevant hospital labels. Transparency techniques can also be used to correct errors. For example, in

1640-641: Is a body of knowledge represented in a form that can be used by a program. An ontology is the set of objects, relations, concepts, and properties used by a particular domain of knowledge. Knowledge bases need to represent things such as objects, properties, categories, and relations between objects; situations, events, states, and time; causes and effects; knowledge about knowledge (what we know about what other people know); default reasoning (things that humans assume are true until they are told differently and will remain true even when other facts are changing); and many other aspects and domains of knowledge. Among

1722-459: Is an input, at least one hidden layer of nodes and an output. Each node applies a function and once the weight crosses its specified threshold, the data is transmitted to the next layer. A network is typically called a deep neural network if it has at least 2 hidden layers. Learning algorithms for neural networks use local search to choose the weights that will get the right output for each input during training. The most common training technique

SECTION 20

#1732798250303

1804-462: Is an interdisciplinary umbrella that comprises systems that recognize, interpret, process, or simulate human feeling, emotion, and mood . For example, some virtual assistants are programmed to speak conversationally or even to banter humorously; it makes them appear more sensitive to the emotional dynamics of human interaction, or to otherwise facilitate human–computer interaction . However, this tends to give naïve users an unrealistic conception of

1886-444: Is an unsolved problem. Knowledge representation and knowledge engineering allow AI programs to answer questions intelligently and make deductions about real-world facts. Formal knowledge representations are used in content-based indexing and retrieval, scene interpretation, clinical decision support, knowledge discovery (mining "interesting" and actionable inferences from large databases ), and other areas. A knowledge base

1968-422: Is anything that perceives and takes actions in the world. A rational agent has goals or preferences and takes actions to make them happen. In automated planning , the agent has a specific goal. In automated decision-making , the agent has preferences—there are some situations it would prefer to be in, and some situations it is trying to avoid. The decision-making agent assigns a number to each situation (called

2050-486: Is approaching human-like ( AGI ) and superhuman cognitive capabilities ( ASI ) and could endanger human civilization if misaligned. These risks remain debated. It is common for AI risks (and technological risks more generally) to be categorized as misuse or accidents . Some scholars have suggested that this framework falls short. For example, the Cuban Missile Crisis was not clearly an accident or

2132-413: Is classified based on previous experience. There are many kinds of classifiers in use. The decision tree is the simplest and most widely used symbolic machine learning algorithm. K-nearest neighbor algorithm was the most widely used analogical AI until the mid-1990s, and Kernel methods such as the support vector machine (SVM) displaced k-nearest neighbor in the 1990s. The naive Bayes classifier

2214-500: Is difficult to understand why they make the decisions they do as a result of the massive number of computations they perform. This makes it challenging to anticipate failures. In 2018, a self-driving car killed a pedestrian after failing to identify them. Due to the black box nature of the AI software, the reason for the failure remains unclear. It also raises debates in healthcare over whether statistically efficient but opaque models should be used. One critical benefit of transparency

2296-413: Is labelled by a solution of the problem and whose leaf nodes are labelled by premises or axioms . In the case of Horn clauses , problem-solving search can be performed by reasoning forwards from the premises or backwards from the problem. In the more general case of the clausal form of first-order logic , resolution is a single, axiom-free rule of inference, in which a problem is solved by proving

2378-823: Is often challenging for AI designers to align an AI system because it is difficult for them to specify the full range of desired and undesired behaviors. Therefore, AI designers often use simpler proxy goals , such as gaining human approval . But proxy goals can overlook necessary constraints or reward the AI system for merely appearing aligned. Misaligned AI systems can malfunction and cause harm. AI systems may find loopholes that allow them to accomplish their proxy goals efficiently but in unintended, sometimes harmful, ways ( reward hacking ). They may also develop unwanted instrumental strategies , such as seeking power or survival because such strategies help them achieve their final given goals. Furthermore, they might develop undesirable emergent goals that could be hard to detect before

2460-400: Is reportedly the "most widely used learner" at Google, due in part to its scalability. Neural networks are also used as classifiers. An artificial neural network is based on a collection of nodes also known as artificial neurons , which loosely model the neurons in a biological brain. It is trained to recognise patterns; once trained, it can recognise those patterns in fresh data. There

2542-480: Is the backpropagation algorithm. Neural networks learn to model complex relationships between inputs and outputs and find patterns in data. In theory, a neural network can learn any function. AI safety Beyond technical research, AI safety involves developing norms and policies that promote safety. It gained significant popularity in 2023, with rapid progress in generative AI and public concerns voiced by researchers and CEOs about potential dangers. During

Ai - Misplaced Pages Continue

2624-404: Is the process of proving a new statement ( conclusion ) from other statements that are given and assumed to be true (the premises ). Proofs can be structured as proof trees , in which nodes are labelled by sentences, and children nodes are connected to parent nodes by inference rules . Given a problem and a set of premises, problem-solving reduces to searching for a proof tree whose root node

2706-440: Is used for game-playing programs, such as chess or Go. It searches through a tree of possible moves and counter-moves, looking for a winning position. Local search uses mathematical optimization to find a solution to a problem. It begins with some form of guess and refines it incrementally. Gradient descent is a type of local search that optimizes a set of numerical parameters by incrementally adjusting them to minimize

2788-455: Is used for reasoning and knowledge representation . Formal logic comes in two main forms: propositional logic (which operates on statements that are true or false and uses logical connectives such as "and", "or", "not" and "implies") and predicate logic (which also operates on objects, predicates and relations and uses quantifiers such as " Every X is a Y " and "There are some X s that are Y s"). Deductive reasoning in logic

2870-436: Is used in AI programs that make decisions that involve other agents. Machine learning is the study of programs that can improve their performance on a given task automatically. It has been a part of AI from the beginning. There are several kinds of machine learning. Unsupervised learning analyzes a stream of data and finds patterns and makes predictions without any other guidance. Supervised learning requires labeling

2952-905: Is when the knowledge gained from one problem is applied to a new problem. Deep learning is a type of machine learning that runs inputs through biologically inspired artificial neural networks for all of these types of learning. Computational learning theory can assess learners by computational complexity , by sample complexity (how much data is required), or by other notions of optimization . Natural language processing (NLP) allows programs to read, write and communicate in human languages such as English . Specific problems include speech recognition , speech synthesis , machine translation , information extraction , information retrieval and question answering . Early work, based on Noam Chomsky 's generative grammar and semantic networks , had difficulty with word-sense disambiguation unless restricted to small domains called " micro-worlds " (due to

3034-520: The bar exam , SAT test, GRE test, and many other real-world applications. Machine perception is the ability to use input from sensors (such as cameras, microphones, wireless signals, active lidar , sonar, radar, and tactile sensors ) to deduce aspects of the world. Computer vision is the ability to analyze visual input. The field includes speech recognition , image classification , facial recognition , object recognition , object tracking , and robotic perception . Affective computing

3116-598: The computer age : Moreover, if we move in the direction of making machines which learn and whose behavior is modified by experience, we must face the fact that every degree of independence we give the machine is a degree of possible defiance of our wishes. From 2008 to 2009, the Association for the Advancement of Artificial Intelligence ( AAAI ) commissioned a study to explore and address potential long-term societal influences of AI research and development. The panel

3198-416: The transformer architecture , and by the early 2020s hundreds of billions of dollars were being invested in AI (known as the " AI boom "). The widespread use of AI in the 21st century exposed several unintended consequences and harms in the present and raised concerns about its risks and long-term effects in the future, prompting discussions about regulatory policies to ensure the safety and benefits of

3280-436: The " utility ") that measures how much the agent prefers it. For each possible action, it can calculate the " expected utility ": the utility of all possible outcomes of the action, weighted by the probability that the outcome will occur. It can then choose the action with the maximum expected utility. In classical planning , the agent knows exactly what the effect of any action will be. In most real-world problems, however,

3362-909: The 2023 AI Safety Summit , the United States and the United Kingdom both established their own AI Safety Institute . However, researchers have expressed concern that AI safety measures are not keeping pace with the rapid development of AI capabilities. Scholars discuss current risks from critical systems failures, bias , and AI-enabled surveillance, as well as emerging risks like technological unemployment , digital manipulation, weaponization, AI-enabled cyberattacks and bioterrorism . They also discuss speculative risks from losing control of future artificial general intelligence (AGI) agents, or from AI enabling perpetually stable dictatorships. Some have criticized concerns about AGI, such as Andrew Ng who compared them in 2015 to "worrying about overpopulation on Mars when we have not even set foot on

Ai - Misplaced Pages Continue

3444-601: The US National Security Commission on Artificial Intelligence reported that advances in AI may make it increasingly important to "assure that systems are aligned with goals and values, including safety, robustness and trustworthiness". Subsequently, the National Institute of Standards and Technology drafted a framework for managing AI Risk, which advises that when "catastrophic risks are present – development and deployment should cease in

3526-533: The White House Office of Science and Technology Policy and Carnegie Mellon University announced The Public Workshop on Safety and Control for Artificial Intelligence, which was one of a sequence of four White House workshops aimed at investigating "the advantages and drawbacks" of AI. In the same year, Concrete Problems in AI Safety – one of the first and most influential technical AI Safety agendas –

3608-421: The agent can seek information to improve its preferences. Information value theory can be used to weigh the value of exploratory or experimental actions. The space of possible future actions and situations is typically intractably large, so the agents must take actions and evaluate situations while being uncertain of what the outcome will be. A Markov decision process has a transition model that describes

3690-510: The agent may not be certain about the situation they are in (it is "unknown" or "unobservable") and it may not know for certain what will happen after each possible action (it is not "deterministic"). It must choose an action by making a probabilistic guess and then reassess the situation to see if the action worked. In some problems, the agent's preferences may be uncertain, especially if there are other agents or humans involved. These can be learned (e.g., with inverse reinforcement learning ), or

3772-529: The agent to operate with incomplete or uncertain information. AI researchers have devised a number of tools to solve these problems using methods from probability theory and economics. Precise mathematical tools have been developed that analyze how an agent can make choices and plan, using decision theory , decision analysis , and information value theory . These tools include models such as Markov decision processes , dynamic decision networks , game theory and mechanism design . Bayesian networks are

3854-719: The already imbalanced game between cyber attackers and cyber defenders. This would increase 'first strike' incentives and could lead to more aggressive and destabilizing attacks. In order to mitigate this risk, some have advocated for an increased emphasis on cyber defense. In addition, software security is essential for preventing powerful AI models from being stolen and misused. Recent studies have shown that AI can significantly enhance both technical and managerial cybersecurity tasks by automating routine tasks and improving overall efficiency. The advancement of AI in economic and military domains could precipitate unprecedented political challenges. Some scholars have compared AI race dynamics to

3936-406: The benefit of being able to take perfect measurements and perform arbitrary ablations. ML models can potentially contain 'trojans' or 'backdoors': vulnerabilities that malicious actors maliciously build into an AI system. For example, a trojaned facial recognition system could grant access when a specific piece of jewelry is in view; or a trojaned autonomous vehicle may function normally until

4018-598: The book Superintelligence: Paths, Dangers, Strategies . He has the opinion that the rise of AGI has the potential to create various societal issues, ranging from the displacement of the workforce by AI, manipulation of political and military structures, to even the possibility of human extinction. His argument that future advanced systems may pose a threat to human existence prompted Elon Musk , Bill Gates , and Stephen Hawking to voice similar concerns. In 2015, dozens of artificial intelligence experts signed an open letter on artificial intelligence calling for research on

4100-492: The broader context of safety engineering , structural factors like 'organizational safety culture' play a central role in the popular STAMP risk analysis framework. Inspired by the structural perspective, some researchers have emphasized the importance of using machine learning to improve sociotechnical safety factors, for example, using ML for cyber defense, improving institutional decision-making, and facilitating cooperation. Some scholars are concerned that AI will exacerbate

4182-451: The cold war, where the careful judgment of a small number of decision-makers often spelled the difference between stability and catastrophe. AI researchers have argued that AI technologies could also be used to assist decision-making. For example, researchers are beginning to develop AI forecasting and advisory systems. Many of the largest global threats (nuclear war, climate change, etc.) have been framed as cooperation challenges. As in

SECTION 50

#1732798250303

4264-648: The common sense knowledge problem ). Margaret Masterman believed that it was meaning and not grammar that was the key to understanding languages, and that thesauri and not dictionaries should be the basis of computational language structure. Modern deep learning techniques for NLP include word embedding (representing words, typically as vectors encoding their meaning), transformers (a deep learning architecture using an attention mechanism), and others. In 2019, generative pre-trained transformer (or "GPT") language models began to generate coherent text, and by 2023, these models were able to get human-level scores on

4346-478: The complex challenges posed by advanced AI systems worldwide. Some experts have argued that it is too early to regulate AI, expressing concerns that regulations will hamper innovation and it would be foolish to "rush to regulate in ignorance". Others, such as business magnate Elon Musk , call for pre-emptive action to mitigate catastrophic risks. Outside of formal legislation, government agencies have put forward ethical and safety recommendations. In March 2021,

4428-444: The head of longterm governance and strategy at DeepMind has emphasized the dangers of racing and the potential need for cooperation: "it may be close to a necessary and sufficient condition for AI safety and alignment that there be a high degree of caution prior to deploying advanced powerful systems; however, if actors are competing in a domain with large returns to first-movers or relative advantage, then they will be pressured to choose

4510-440: The intelligence of existing computer agents. Moderate successes related to affective computing include textual sentiment analysis and, more recently, multimodal sentiment analysis , wherein AI classifies the affects displayed by a videotaped subject. A machine with artificial general intelligence should be able to solve a wide variety of problems with breadth and versatility similar to human intelligence . AI research uses

4592-537: The late 1980s and 1990s, methods were developed for dealing with uncertain or incomplete information, employing concepts from probability and economics . Many of these algorithms are insufficient for solving large reasoning problems because they experience a "combinatorial explosion": They become exponentially slower as the problems grow. Even humans rarely use the step-by-step deduction that early AI research could model. They solve most of their problems using fast, intuitive judgments. Accurate and efficient reasoning

4674-438: The long-term risk of non-aligned Artificial General Intelligence, and the unforeseeable changes that it would mean for ... the world, seriously". The strategy describes actions to assess long-term AI risks, including catastrophic risks. The British government held first major global summit on AI safety. This took place on the 1st and 2 November 2023 and was described as "an opportunity for policymakers and world leaders to consider

4756-408: The model to make a mistake". For example, in 2013, Szegedy et al. discovered that adding specific imperceptible perturbations to an image could cause it to be misclassified with high confidence. This continues to be an issue with neural networks, though in recent work the perturbations are generally large enough to be perceptible. All of the images on the right are predicted to be an ostrich after

4838-457: The most difficult problems in knowledge representation are the breadth of commonsense knowledge (the set of atomic facts that the average person knows is enormous); and the sub-symbolic form of most commonsense knowledge (much of what people know is not represented as "facts" or "statements" that they could express verbally). There is also the difficulty of knowledge acquisition , the problem of obtaining knowledge for AI applications. An "agent"

4920-456: The necessity of scaling local safety measures to a global level, proposing a classification for these global solutions. This approach underscores the importance of collaborative efforts in the international governance of AI safety, emphasizing that no single entity can effectively manage the risks associated with AI technologies. This perspective aligns with ongoing efforts in international policy-making and regulatory frameworks, which aim to address

5002-532: The need for research projects that contribute positively towards an equitable technological ecosystem. AI governance is broadly concerned with creating norms, standards, and regulations to guide the use and development of AI systems. AI safety governance research ranges from foundational investigations into the potential impacts of AI to specific applications. On the foundational side, researchers have argued that AI could transform many aspects of society due to its broad applicability, comparing it to electricity and

SECTION 60

#1732798250303

5084-547: The opaqueness of AI systems is a significant source of risk and better understanding of how they function could prevent high-consequence failures in the future. "Inner" interpretability research aims to make ML models less opaque. One goal of this research is to identify what the internal neuron activations represent. For example, researchers identified a neuron in the CLIP artificial intelligence system that responds to images of people in spider man costumes, sketches of spiderman, and

5166-405: The other hand. Classifiers are functions that use pattern matching to determine the closest match. They can be fine-tuned based on chosen examples using supervised learning . Each pattern (also called an " observation ") is labeled with a certain predefined class. All the observations combined with their class labels are known as a data set . When a new observation is received, that observation

5248-697: The paper "Locating and Editing Factual Associations in GPT", the authors were able to identify model parameters that influenced how it answered questions about the location of the Eiffel tower. They were then able to 'edit' this knowledge to make the model respond to questions as if it believed the tower was in Rome instead of France. Though in this case, the authors induced an error, these methods could potentially be used to efficiently fix them. Model editing techniques also exist in computer vision. Finally, some have argued that

5330-616: The perturbation is applied. (Left) is a correctly predicted sample, (center) perturbation applied magnified by 10x, (right) adversarial example. Adversarial robustness is often associated with security. Researchers demonstrated that an audio signal could be imperceptibly modified so that speech-to-text systems transcribe it to any message the attacker chooses. Network intrusion and malware detection systems also must be adversarially robust since attackers may design their attacks to fool detectors. Models that represent objectives (reward models) must also be adversarially robust. For example,

5412-409: The planet yet". Stuart J. Russell on the other side urges caution, arguing that "it is better to anticipate human ingenuity than to underestimate it". AI researchers have widely differing opinions about the severity and primary sources of risk posed by AI technology – though surveys suggest that experts take high consequence risks seriously. In two surveys of AI researchers, the median respondent

5494-411: The probability that a particular action will change the state in a particular way and a reward function that supplies the utility of each state and the cost of each action. A policy associates a decision with each possible state. The policy could be calculated (e.g., by iteration ), be heuristic , or it can be learned. Game theory describes the rational behavior of multiple interacting agents and

5576-974: The risks of misuse and loss of control associated with frontier AI models. During the summit the intention to create the International Scientific Report on the Safety of Advanced AI was announced. In 2024, The US and UK forged a new partnership on the science of AI safety. The MoU was signed on 1 April 2024 by US commerce secretary Gina Raimondo and UK technology secretary Michelle Donelan to jointly develop advanced AI model testing, following commitments announced at an AI Safety Summit in Bletchley Park in November. AI safety research areas include robustness, monitoring, and alignment. AI systems are often vulnerable to adversarial examples or "inputs to machine learning (ML) models that an attacker has intentionally designed to cause

5658-697: The societal impacts of AI and outlining concrete directions. To date, the letter has been signed by over 8000 people including Yann LeCun , Shane Legg , Yoshua Bengio , and Stuart Russell . In the same year, a group of academics led by professor Stuart Russell founded the Center for Human-Compatible AI at the University of California Berkeley and the Future of Life Institute awarded $ 6.5 million in grants for research aimed at "ensuring artificial intelligence (AI) remains safe, ethical and beneficial". In 2016,

5740-430: The steam engine. Some work has focused on anticipating specific risks that may arise from these impacts – for example, risks from mass unemployment, weaponization, disinformation, surveillance, and the concentration of power. Other work explores underlying risk factors such as the difficulty of monitoring the rapidly evolving AI industry, the availability of AI models, and 'race to the bottom' dynamics. Allan Dafoe,

5822-537: The system is deployed and encounters new situations and data distributions . Today, some of these issues affect existing commercial systems such as large language models , robots , autonomous vehicles , and social media recommendation engines . Some AI researchers argue that more capable future systems will be more severely affected because these problems partially result from high capabilities. Many prominent AI researchers, including Geoffrey Hinton , Yoshua Bengio , and Stuart Russell , argue that AI

5904-471: The technology . The general problem of simulating (or creating) intelligence has been broken into subproblems. These consist of particular traits or capabilities that researchers expect an intelligent system to display. The traits described below have received the most attention and cover the scope of AI research. Early researchers developed algorithms that imitated step-by-step reasoning that humans use when they solve puzzles or make logical deductions . By

5986-451: The training data with the expected answers, and comes in two main varieties: classification (where the program must learn to predict what category the input belongs in) and regression (where the program must deduce a numeric function based on numeric input). In reinforcement learning , the agent is rewarded for good responses and punished for bad ones. The agent learns to choose responses that are classified as "good". Transfer learning

6068-402: The true proportion that the model is correct. Similarly, anomaly detection or out-of-distribution (OOD) detection aims to identify when an AI system is in an unusual situation. For example, if a sensor on an autonomous vehicle is malfunctioning, or it encounters challenging terrain, it should alert the driver to take control or pull over. Anomaly detection has been implemented by simply training

6150-420: The use of particular tools. The traditional goals of AI research include reasoning , knowledge representation , planning , learning , natural language processing , perception, and support for robotics . General intelligence —the ability to complete any task performable by a human on an at least equal level—is among the field's long-term goals. To reach these goals, AI researchers have adapted and integrated

6232-686: The way they interact. In recent years, the development of large language models (LLMs) has raised unique concerns within the field of AI safety. Researchers Bender and Gebru et al. have highlighted the environmental and financial costs associated with training these models, emphasizing that the energy consumption and carbon footprint of training procedures like those for Transformer models can be substantial. Moreover, these models often rely on massive, uncurated Internet-based datasets, which can encode hegemonic and biased viewpoints, further marginalizing underrepresented groups. The large-scale training data, while vast, does not guarantee diversity and often reflects

6314-493: The well-known prisoner's dilemma scenario, some dynamics may lead to poor results for all players, even when they are optimally acting in their self-interest. For example, no single actor has strong incentives to address climate change even though the consequences may be significant if no one intervenes. A salient AI cooperation challenge is avoiding a 'race to the bottom'. In this scenario, countries or companies race to build more capable AI systems and neglect safety, leading to

6396-432: The word 'spider'. It also involves explaining connections between these neurons or 'circuits'. For example, researchers have identified pattern-matching mechanisms in transformer attention that may play a role in how language models learn from their context. "Inner interpretability" has been compared to neuroscience. In both cases, the goal is to understand what is going on in an intricate system, though ML researchers have

6478-663: The worldviews of privileged demographics, leading to models that perpetuate existing biases and stereotypes. This situation is exacerbated by the tendency of these models to produce seemingly coherent and fluent text, which can mislead users into attributing meaning and intent where none exists, a phenomenon described as 'stochastic parrots'. These models, therefore, pose risks of amplifying societal biases, spreading misinformation, and being used for malicious purposes, such as generating extremist propaganda or deepfakes. To address these challenges, researchers advocate for more careful planning in dataset creation and system development, emphasizing

6560-674: Was generally skeptical of the radical views expressed by science-fiction authors but agreed that "additional research would be valuable on methods for understanding and verifying the range of behaviors of complex computational systems to minimize unexpected outcomes". In 2011, Roman Yampolskiy introduced the term "AI safety engineering" at the Philosophy and Theory of Artificial Intelligence conference, listing prior failures of AI systems and arguing that "the frequency and seriousness of such events will steadily increase as AIs become more capable". In 2014, philosopher Nick Bostrom published

6642-411: Was optimistic about AI overall, but placed a 5% probability on an "extremely bad (e.g. human extinction )" outcome of advanced AI. In a 2022 survey of the natural language processing community, 37% agreed or weakly agreed that it is plausible that AI decisions could lead to a catastrophe that is "at least as bad as an all-out nuclear war". Risks from AI began to be seriously discussed at the start of

6724-654: Was published. In 2017, the Future of Life Institute sponsored the Asilomar Conference on Beneficial AI , where more than 100 thought leaders formulated principles for beneficial AI including "Race Avoidance: Teams developing AI systems should actively cooperate to avoid corner-cutting on safety standards". In 2018, the DeepMind Safety team outlined AI safety problems in specification, robustness, and assurance. The following year, researchers organized

#302697