Computer operating systems (OSes) provide a set of functions needed and used by most application programs on a computer, and the links needed to control and synchronize computer hardware. On the first computers, with no operating system, every program needed the full hardware specification to run correctly and perform standard tasks, and its own drivers for peripheral devices like printers and punched paper card readers. The growing complexity of hardware and application programs eventually made operating systems a necessity for everyday use. == Background == Early computers lacked any form of operating system. Instead, the user (rarely also the computer operator), had sole use of the machine for a scheduled period of time. The user would deliver his program to a computer operator who would be responsible for loading the computer with the program and data needed for its 'run'. Eventually, the end of a user's program could be detected and a control program automatically loaded which would load the next user's program, relieving the operator of having to load in each user's program individually and introducing the era of 'batched' programming. That is, a number of user programs could all be loaded together in a batch. Loading of program and data was accomplished in various ways including toggle switches (only used by a user on the earliest of computers, but later used by the computer operator to control the computer, e.g., to start it up, to shut it down, to 'pause', to 'dump' its RAM contents, and/or to control its input and/or its output), punched paper cards and magnetic or paper tape. Once loaded, the machine would be set to execute each program singly until that program completed, crashed, exceeded its time limit or went into a(n infinite) loop. In those early days, there were only 'Control Program' units for providing the software necessary to control the computers and ancillary hardware, e.g., for such semi hardware functions as I/O . None of the early 'Control Programs' were sufficiently sophisticated to recognize a looping user program or initiate a recovery action. Detection and recovery from a looping program was another critical operator function and was usually detected by the sound of the looping computer, whereupon the operator would simply initiate a complete dump of the executing program (for later debugging by the programmer) and then load in (or instruct the computer to go on to) the next user's program. Programs could sometimes be debugged via a control panel using dials, toggle switches and panel lights, making it a very manual and error-prone process. But, this was quite rare, since the high cost of even the simplest of the early computers prohibited such exclusive use of a computer by an individual programmer. Almost all program debugging was done away from any computer by the original programmer perusing the program and the dump of its execution obtained, e.g., by the computer operator or automatically by some computer hardware exception detection (such as a timeout, an attempt to divide by zero, or an over or underflow). Programmers then could only very rarely have more than one computer 'run' per day! Symbolic languages, e.g., assemblers and compilers were developed for programmers to translate symbolic program code into machine code that previously would have been hand-encoded. Later machines came with libraries of support code on punched cards or magnetic tape, which would be linked to the user's program to assist in operations such as input and output. This was the genesis of the modern-day operating system; however, machines still ran a single program or job at a time. At Cambridge University in England the job queue was at one time a string from which tapes attached to corresponding job tickets were hung with stationery pegs. == Mainframes == The first operating system used for real work was GM-NAA I/O, produced in 1956 by General Motors' Research division for its IBM 704. Most other early operating systems for IBM mainframes were also produced by customers. Early operating systems were very diverse, with each vendor or customer producing one or more operating systems specific to their particular mainframe computer. Every operating system, even from the same vendor, could have radically different models of commands, operating procedures, and such facilities as debugging aids. Typically, each time the manufacturer brought out a new machine, there would be a new operating system, and most applications would have to be manually adjusted, recompiled, and retested. === Systems on IBM hardware === Building on customer experience and requirements, IBM took on a more active role in developing operating systems for the 709, 1410, 7010, 7040, 7044, 7090 and 7094. IBM also collaborated with universities. The state of affairs continued until the mid 1960s when IBM, already a leading hardware vendor, stopped work on existing systems and put all its effort into developing the System/360 series of machines, all of which used the same instruction and input/output architecture. IBM intended to develop a single operating system for the new hardware, the OS/360. The problems encountered in the development of the OS/360 are legendary, and are described by Fred Brooks in The Mythical Man-Month—a book that has become a classic of software engineering. Because of performance differences across the hardware range and delays with software development, a whole family of operating systems was introduced instead of a single OS/360. IBM wound up releasing a series of stop-gaps followed by two longer-lived operating systems: OS/360 for mid-range and large systems. This was available in three system generation options: PCP for early users and for those without the resources for multiprogramming. MFT for mid-range systems, replaced by MFT-II in OS/360 Release 15/16. This had one successor, OS/VS1, which was discontinued in the 1980s. MVT for large systems. This was similar in most ways to PCP and MFT (most programs could be ported among the three without being re-compiled), but has more sophisticated memory management and a time-sharing facility, TSO. MVT had several successors including the current z/OS. DOS/360 for small System/360 models had several successors including the current z/VSE. It was significantly different from OS/360. IBM maintained full compatibility with the past, so that programs developed in the sixties can still run under z/VSE (if developed for DOS/360) or z/OS (if developed for MFT or MVT) with no change. IBM also developed TSS/360, a time-sharing system for the System/360 Model 67. Overcompensating for their perceived importance of developing a timeshare system, they set hundreds of developers to work on the project. Early releases of TSS were slow and unreliable; by the time TSS had acceptable performance and reliability, IBM wanted its TSS users to migrate to OS/360 and OS/VS2; while IBM offered a TSS/370 PRPQ, they dropped it after 3 releases. Several operating systems for the IBM S/360 and S/370 architectures were developed by third parties, including the Michigan Terminal System (MTS) and MUSIC/SP. === Other mainframe operating systems === Control Data Corporation developed the SCOPE operating systems in the 1960s, for batch processing and later developed the MACE operating system for time sharing, which was the basis for the later Kronos. In cooperation with the University of Minnesota, the Kronos and later the NOS operating systems were developed during the 1970s, which supported simultaneous batch and time sharing use. Like many commercial time sharing systems, its interface was an extension of the DTSS time sharing system, one of the pioneering efforts in timesharing and programming languages. In the late 1970s, Control Data and the University of Illinois developed the PLATO system, which used plasma panel displays and long-distance time sharing networks. PLATO was remarkably innovative for its time; the shared memory model of PLATO's TUTOR programming language allowed applications such as real-time chat and multi-user graphical games. For the UNIVAC 1107, UNIVAC, the first commercial computer manufacturer, produced the EXEC I operating system, and Computer Sciences Corporation developed the EXEC II operating system and delivered it to UNIVAC. EXEC II was ported to the UNIVAC 1108. Later, UNIVAC developed the EXEC 8 operating system for the 1108; it was the basis for operating systems for later members of the family. Like all early mainframe systems, EXEC I and EXEC II were a batch-oriented system that managed magnetic drums, disks, card readers and line printers; EXEC 8 supported both batch processing and on-line transaction processing. In the 1970s, UNIVAC produced the Real-Time Basic (RTB) system to support large-scale time sharing, also patterned after the Dartmouth BASIC system. Burroughs Corporation introduced the B5000 in 1961 with the MCP (Master Control Program) operating system. The B5000
LMArena
Arena (formerly LMArena and Chatbot Arena) is a public, web-based platform that evaluates large language models (LLMs). Users enter prompts for two anonymous models to respond to and vote on the model that gave the better response, after which the models' identities are revealed. Users can also choose models to test themselves via the "Direct" selection. Companies which have supplied the company with their large language models include OpenAI, Google DeepMind, and Anthropic. The website has been used for preview releases of upcoming models. Chinese company DeepSeek tested its prototype models in the Arena months before its R1 model gained attention in Western media. Other notable pre-release models include OpenAI's GPT-5 under the codename "summit" and Google DeepMind's Gemini 2.5 Flash Image (an image-generation and editing model) under the codename "Nano Banana". Research has identified specific limitations in Arena's methodology. == History == Chatbot Arena was released on April 24, 2023. In June 2024, Chatbot Arena added image support. In September 2024, Chatbot Arena moved to its own dedicated domain name, lmarena.ai (or LMArena). In April 2025, Meta released Llama 4. Llama 4 Maverick beat GPT-4o and Gemini 2.0 Flash on LMArena, but the version of Maverick on LMArena unfairly differed from the publicly available version. LMArena updated their policies in response. In April 2025, LMArena incorporated as an independent company. That May, LMArena raised $100 million in a seed funding round, valuing the company at $600 million. Participants in the seed funding round included Andreessen Horowitz, UC Investments, Lightspeed Venture Partners, Felicis Ventures, and Kleiner Perkins. On January 6, 2026, LMArena announced the closing of a $150 million Series A funding round, bringing the company’s post-money valuation to approximately $1.7 billion. The round was led by Felicis and UC Investments (University of California), with participation from Andreessen Horowitz, The House Fund, LDVP, Kleiner Perkins, Lightspeed Venture Partners, and Laude Ventures. In January 2026, LMArena added video support. On January 28, 2026, LMArena rebranded to "Arena".
Recommender system
A recommender system, also called a recommendation algorithm, recommendation engine, or recommendation platform, is a type of information filtering system that suggests items most relevant to a particular user. The value of these systems becomes particularly evident in scenarios where users must select from a large number of options, such as products, media, or content. Major social media platforms and streaming services rely on recommender systems that employ machine learning to analyze user behavior and preferences, thereby enabling personalized content feeds. Typically, the suggestions refer to a variety decision-making processes, including the selection of a product, musical selection, or online news source to read. The implementation of recommender systems is pervasive, with commonly recognised examples including the generation of playlist for video and music services, the provision of product recommendations for e-commerce platforms, and the recommendation of content on social media platforms and the open web. These systems can operate using a single type of input, such as music, or multiple inputs from diverse platforms, including news, books and search queries. Additionally, popular recommender systems have been developed for specific topics, such as restaurants and online dating services. Recommender systems have also been developed to explore research articles and experts, collaborators, and financial services. A content discovery platform is a software recommendation platform that employs recommender system tools. It utilizes user metadata in order to identify and suggest relevant content, whilst reducing ongoing maintenance and development costs. A content discovery platform delivers personalized content to websites, mobile devices, and set-top boxes. A large range of content discovery platforms currently exist for various forms of content ranging from news articles and academic journal articles to television. As operators compete to serve as the gateway to home entertainment, personalized television emerges as a key service differentiator. Academic content discovery has recently become another area of interest, the emergence of numerous companies dedicated to assisting academic researchers in keeping up to date with relevant academic content and facilitating serendipitous discovery of new content. == Overview == Recommender systems usually make use of either or both collaborative filtering and content-based filtering, as well as other systems such as knowledge-based systems. Collaborative filtering approaches build a model from a user's past behavior (e.g., items previously purchased or selected and/or numerical ratings given to those items) as well as similar decisions made by other users. This model is then used to predict items (or ratings for items) that the user may have an interest in. Content-based filtering approaches utilize a series of discrete, pre-tagged characteristics of an item in order to recommend additional items with similar properties. === Example === The differences between collaborative and content-based filtering can be demonstrated by comparing two early music recommender systems, Last.fm and Pandora Radio. We can also look at how these methods are applied in e-commerce, for example, on platforms like Amazon. Last.fm creates a "station" of recommended songs by observing what bands and individual tracks the user has listened to on a regular basis and comparing those against the listening behavior of other users. Last.fm will play tracks that do not appear in the user's library, but are often played by other users with similar interests. As this approach leverages the behavior of users, it is an example of a collaborative filtering technique. Pandora uses the properties of a song or artist (a subset of the 450 attributes provided by the Music Genome Project) to seed a "station" that plays music with similar properties. User feedback is used to refine the station's results, deemphasizing certain attributes when a user "dislikes" a particular song and emphasizing other attributes when a user "likes" a song. This is an example of a content-based approach. In e-commerce, Amazon's well-known "customers who bought X also bought Y" feature is a prime example of collaborative filtering. It also uses content-based filtering when it recommends a book by the same author you've previously read or a pair of shoes in a similar style to ones you've viewed. Each type of system has its strengths and weaknesses. In the above example, Last.fm requires a large amount of information about a user to make accurate recommendations. This is an example of the cold start problem, and is common in collaborative filtering systems. Whereas Pandora needs very little information to start, it is far more limited in scope (for example, it can only make recommendations that are similar to the original seed). === Alternative implementations === Recommender systems are a useful alternative to search algorithms since they help users discover items they might not have found otherwise. Of note, recommender systems are often implemented using search engines indexing non-traditional data. In some cases, like in the Gonzalez v. Google Supreme Court case, may argue that search and recommendation algorithms are different technologies. Recommender systems have been the focus of several granted patents, and there are more than 50 software libraries that support the development of recommender systems including LensKit, RecBole, ReChorus and RecPack. == History == Elaine Rich created the first recommender system in 1979, called Grundy. She looked for a way to recommend users books they might like. Her idea was to create a system that asks users specific questions and classifies them into classes of preferences, or "stereotypes", depending on their answers. Depending on users' stereotype membership, they would then get recommendations for books they might like. Another early recommender system, called a "digital bookshelf", was described in a 1990 technical report by Jussi Karlgren at Columbia University, and implemented at scale and worked through in technical reports and publications from 1994 onwards by Jussi Karlgren, then at SICS, and research groups led by Pattie Maes at MIT, Will Hill at Bellcore, and Paul Resnick, also at MIT, whose work with GroupLens was awarded the 2010 ACM Software Systems Award. Montaner provided the first overview of recommender systems from an intelligent agent perspective. Adomavicius provided a new, alternate overview of recommender systems. Herlocker provides an additional overview of evaluation techniques for recommender systems, and Beel et al. discussed the problems of offline evaluations. Beel et al. have also provided literature surveys on available research paper recommender systems and existing challenges. == Approaches == === Collaborative filtering === One approach to the design of recommender systems that has wide use is collaborative filtering. Collaborative filtering is based on the assumption that people who agreed in the past will agree in the future, and that they will like similar kinds of items as they liked in the past. The system generates recommendations using only information about rating profiles for different users or items. By locating peer users/items with a rating history similar to the current user or item, they generate recommendations using this neighborhood. This approach is a cornerstone for e-commerce sites that analyze the purchasing patterns of thousands of users to suggest what you might like. Collaborative filtering methods are classified as memory-based and model-based. A well-known example of memory-based approaches is the user-based algorithm, while that of model-based approaches is matrix factorization (recommender systems). A key advantage of the collaborative filtering approach is that it does not rely on machine analyzable content and therefore it is capable of accurately recommending complex items such as movies without requiring an "understanding" of the item itself. Many algorithms have been used in measuring user similarity or item similarity in recommender systems. For example, the k-nearest neighbor (k-NN) approach and the Pearson Correlation as first implemented by Allen. When building a model from a user's behavior, a distinction is often made between explicit and implicit forms of data collection. Examples of explicit data collection include the following: Asking a user to rate an item on a sliding scale. Asking a user to search. Asking a user to rank a collection of items from favorite to least favorite. Presenting two items to a user and asking him/her to choose the better one of them. Asking a user to create a list of items that he/she likes (see Rocchio classification or other similar techniques). Examples of implicit data collection include the following: Observing the items that a user views in an online store, media library, or other repository of med
Literature review
A literature review is an overview of previously published works on a particular topic. The term can refer to a full scholarly paper or a section of a scholarly work such as books or articles. Either way, a literature review provides the researcher/author and the audiences with general information of an existing knowledge of a particular topic. A good literature review has a proper research question, a proper theoretical framework, and/or a chosen research method. It serves to situate the current study within the body of the relevant literature and provides context for the reader. In such cases, the review usually precedes the methodology and results sections of the work. Producing a literature review is often part of a graduate and post-graduate requirement, included in the preparation of a thesis, dissertation, or a journal article. Literature reviews are also common in a research proposal or prospectus (the document approved before a student formally begins a dissertation or thesis). A literature review can be a type of a review article. In this sense, it is a scholarly paper that presents the current knowledge including substantive findings as well as theoretical and methodological contributions to a particular topic. Literature reviews are secondary sources and do not report new or original experimental work. Most often associated with academic-oriented literature, such reviews are found in academic journals and are not to be confused with book reviews, which may also appear in the same publication. Literature reviews are a basis for research in nearly every academic field. == Types == Since the concept of a systematic review was formalized in the 1970s, a basic division among types of reviews is the dichotomy of narrative reviews versus systematic reviews. The main types of narrative reviews are evaluative, exploratory, and instrumental. A fourth type of review of literature (the scientific literature) is the systematic review but it is not called a literature review, which absent further specification, conventionally refers to narrative reviews. A systematic review focuses on a specific research question to identify, appraise, select, and synthesize all high-quality research evidence and arguments relevant to that question. A meta-analysis is typically a systematic review using statistical methods to effectively combine the data used on all selected studies to produce a more reliable result. Torraco (2016) describes an integrative literature review. The purpose of an integrative literature review is to generate new knowledge on a topic through the process of review, critique, and synthesis of the literature under investigation. George et al (2023) offer an extensive overview of review approaches. They also propose a model for selecting an approach by looking at the purpose, object, subject, community, and practices of the review. They describe six different types of review, each with their own unique purposes: Exploratory or scoping reviews focus on breadth as opposed to depth Systematic or integrative reviews integrate empirical studies on a topic Meta-narrative reviews are qualitative and use literature to compare research or practice communities Problematizing or critical reviews propose new perspectives on a concept by association with other literature Meta-analyses and meta-regressions integrate quantitative studies and identify moderators Mixed research syntheses combine other review approaches in the same paper == Process and product == Shields and Rangarajan (2013) distinguish between the process of reviewing the literature and a finished work or product known as a literature review. The process of reviewing the literature is often ongoing and informs many aspects of the empirical research project. The process of reviewing the literature requires different kinds of activities and ways of thinking. Shields and Rangarajan (2013) and Granello (2001) link the activities of doing a literature review with Benjamin Bloom's revised taxonomy of the cognitive domain (ways of thinking: remembering, understanding, applying, analyzing, evaluating, and creating). === Use of artificial intelligence in a literature review === Artificial intelligence (AI) is reshaping traditional literature reviews across various disciplines. Generative pre-trained transformers, such as ChatGPT, are often used by students and academics for review purposes. Since 2023, an increasing number of tools powered by large language models and other artificial intelligence technologies have been developed to assist, automate, or generate literature reviews. Nevertheless, the employment of ChatGPT in academic reviews is problematic due to ChatGPT's propensity to "hallucinate". In response, efforts are being made to mitigate these hallucinations through the integration of plugins. For instance, Rad et al. (2023) used ScholarAI for review in cardiothoracic surgery.
Voiceverse NFT plagiarism scandal
In January 2022, 15—the pseudonymous Massachusetts Institute of Technology (MIT) artificial intelligence researcher and creator of the non-commercial generative artificial intelligence voice synthesis research project 15.ai—discovered that the blockchain-based technology company Voiceverse had plagiarized from their platform. Voiceverse marketed itself as a service that offered AI voice cloning technology that could be purchased and traded as non-fungible tokens (NFTs). Amid heightened controversy over NFTs in the gaming industry, voice actor Troy Baker (who has been described as one of the most famous voice actors in video games) announced his partnership with Voiceverse on January 14, 2022, triggering immediate backlash over concerns about the environmental impact of NFTs, potential for fraud, predatory monetization in video games, and the potential of AI displacing jobs for human voice actors. Later that same day, 15 revealed through server logs that Voiceverse had generated voice lines using 15's free text-to-speech platform, pitch-shifted the audio to make them unrecognizable, and falsely marketed the samples as their own technology before selling them as NFTs. Within an hour of being confronted with evidence, Voiceverse confessed and stated that their marketing team had used 15.ai without proper attribution while rushing to create a technology demo to coincide with Baker's partnership announcement, further exacerbating the already negative reception to the original announcement. In response, 15 replied "Go fuck yourself"; the interaction went viral and garnered a large amount of support for the developer. News publications universally characterized this incident as Voiceverse having "stolen" from 15.ai. The next day, Baker appeared on a podcast and stated that his motivation had been to help independent creators who were unable to afford professional voice actors. Following continued backlash and the plagiarism revelation, Baker ended his partnership with Voiceverse on January 31, 2022. Subsequently, the incident was documented in multiple AI ethics databases, criticisms of predatory monetization in video games, and retrospectives as one of the earliest instances of plagiarism and theft stemming from artificial intelligence during the AI boom. == Background == === Troy Baker === Troy Baker is a prominent voice actor in the video game industry best known for his performances as Joel Miller in The Last of Us franchise. Baker has been described as "ubiquitous" by Polygon, "one of the most high-profile and prolific voice actors in video games" by Eurogamer, and "arguably the most famous voice actor in the gaming industry" by GameGuru. His other prominent roles include voicing Agent John "Jonesy" Jones in Fortnite, Booker DeWitt in BioShock Infinite, and both Batman and Joker in multiple Batman video games. As of October 2025, Baker holds the record for the most acting nominations at the BAFTA Games Awards, with five between 2013 and 2021. === Voiceverse === Voiceverse is a blockchain-based startup founded by the Bored Ape Yacht Club that marketed itself as offering AI voice cloning technology in the form of NFTs. Prior to the announcement of their partnership with Baker, Voiceverse had partnered with LOVO, Inc., an AI voice platform that, according to LOVO, could generate human-like voices. Voiceverse stated that any user who purchases a voice NFT would have unlimited and perpetual access to the voice model, which could be used to create content such as audiobooks, YouTube videos, podcasts, e-learning materials, in-game voice chat, and Zoom calls. Voiceverse promised that buyers would "OWN [sic] all of the IP" of content they created using these voices. Voiceverse's roadmap included plans to release 8,888 initial voice NFTs, a feature to add emotions to existing voices, and the ability for users to mint their own voices as NFTs. Prior to Baker's partnership, Voiceverse had also partnered with voice actors Charlet Chung, who voices D.Va in Overwatch, and Andy Milonakis of The Andy Milonakis Show. === 15.ai === 15.ai is a free web application launched in 2020 that uses artificial intelligence to generate text-to-speech voices of fictional characters from popular media. Created by a pseudonymous artificial intelligence researcher known as 15, who began developing the technology as a freshman during their undergraduate research at MIT, it was an early example of an application of generative artificial intelligence during the initial stages of the AI boom. The platform showed that deep neural networks could generate emotionally expressive speech with only 15 seconds of speech; the name "15.ai" references the creator's statement that a voice can be convincingly cloned with just 15 seconds of audio, as opposed to the tens of hours of data previously required. 15.ai became an Internet phenomenon in early 2021 when content utilizing it went viral on social media and quickly gained widespread use among various Internet fandoms. 15 has emphasized that it remain free and non-commercial; it only requires users to give proper credit when using the service for content creation. === NFTs in the video game industry === By early 2022, NFTs had become highly controversial within the gaming industry. Critics raised concerns about their environmental impact due to the significant energy consumption of blockchain technology. In addition, the prevalence of scams, fraud, and potential money laundering associated with NFT sales, as well as fears that NFTs were a new form of predatory monetization following the increasing frequency of loot boxes, caused vocal pushback from the gaming community. Several major gaming companies had begun exploring NFT integration into their products, though fan backlash had already forced some projects to be cancelled. On December 16, 2021, the developers of S.T.A.L.K.E.R. 2: Heart of Chernobyl announced that they would be including NFTs in the game, but cancelled within an hour of the announcement due to immediate universal backlash. Simultaneously, the rise of AI voice technology raised concerns among voice actors about potential job displacement and the devaluation of their work amidst the voice acting industry's ongoing struggles for better compensation and working conditions. == Partnership announcement and backlash == On January 14, 2022, 1:02 a.m. EST, Baker announced on Twitter that he was partnering with Voiceverse "to explore ways where together we might bring new tools to new creators to make new things, and allow everyone a chance to own & invest in the IP's they create." The announcement concluded with the statement "You can hate. Or you can create." Baker's specific role with Voiceverse remained unclear at the time of the announcement. Along with Baker's announcement, Voiceverse promoted their supposed voice AI technology on Twitter by posting animated videos that featured a cat character created by NFT firm Chubbiverse. The videos concluded with text that read "The Voice Powered By Voiceverse"; Voiceverse stated on Twitter that the voices in the animations had been generated using their own AI voice synthesis technology and presented the videos as a technology demonstration of their voice NFT capabilities. The announcement provoked immediate and widespread backlash from the gaming community. Baker's tweet received thousands of replies and quote retweets (the vast majority of which were negative), far more than the number of likes; Michael McWhertor of Polygon described it as a "textbook example of being ratioed" and commented that reactions had been amplified by the final part of Baker's announcement. Michael Beckwith of Metro called Baker's approach "bizarrely aggressive". Later that day, Baker responded to the backlash by apologizing for his choice of words. He said he appreciated people's thoughts and acknowledged that the "hate/create part might have been a bit antagonistic," calling it a "bad attempt to bring levity". Despite the apology, Baker and his fellow voice actors did not distance themselves from Voiceverse at this point. At the same time, Voiceverse attempted to address the criticisms, stating that they were working to move to more environmentally friendly blockchain technology and that voice actors would receive royalties from NFT sales, with actors benefiting from any increase in NFT value. == Plagiarism revelation == On December 13, 2021, amidst the increasingly negative reactions toward NFTs among the general public, the creator of 15.ai (known pseudonymously as 15) announced that they had "no interest in incorporating NFTs into any aspect of [their] work." On January 14, 2022, 11:17 a.m. EST (10 hours after Baker's initial announcement), 15 commented on the Voiceverse venture, stating that it "sounds like a scam". Two hours later, at 1:20 p.m., 15 explicitly accused Voiceverse of "actively attempting to appropriate [15's] work for [Voiceverse's] own benefit." 15 provided evidence through
Artificial general intelligence
Artificial general intelligence (AGI) is a hypothetical type of artificial intelligence that matches or surpasses human capabilities across virtually all cognitive tasks. Beyond AGI, artificial superintelligence (ASI) would outperform the best human abilities across every domain by a wide margin. Unlike artificial narrow intelligence (ANI), whose competence is confined to well‑defined tasks, an AGI system can generalise knowledge, transfer skills between domains, and solve novel problems without task‑specific reprogramming. Creating AGI is a stated goal of technology companies such as OpenAI, Google, xAI, and Meta. A 2020 survey identified 72 active AGI research and development projects across 37 countries. AGI is a common topic in science fiction and futures studies. Contention exists over whether AGI represents an existential risk. Some AI experts and industry figures have stated that mitigating the risk of human extinction posed by AGI should be a global priority. Others find the development of AGI to be in too remote a stage to present such a risk. == Terminology == AGI is also known as strong AI, full AI, human-level AI, human-level intelligent AI, or general intelligent action. The term "artificial general intelligence" was used in 1997 by Mark Gubrud in a discussion of the implications of fully automated military production and operations. A mathematical formalism of AGI named AIXI was proposed in 2000 by Marcus Hutter, who defines intelligence as "an agent’s ability to achieve goals or succeed in a wide range of environments". This type of AGI has also been called "universal artificial intelligence". The term AGI was re-introduced and popularized by Shane Legg and Ben Goertzel around 2002. Some academic sources reserve the term "strong AI" for computer programs that will experience sentience or consciousness. In contrast, weak AI (or narrow AI) can solve a specific problem but lacks general cognitive abilities. Some academic sources use "weak AI" to refer more broadly to any programs that neither experience consciousness nor have a mind in the same sense as humans. Related concepts include artificial superintelligence and transformative AI. An artificial superintelligence (ASI) is a hypothetical type of AGI that is much more generally intelligent than humans, while the notion of transformative AI relates to AI having a large impact on society, for example, similar to the agricultural or industrial revolution. A framework for classifying AGI was proposed in 2023 by Google DeepMind researchers. They define five performance levels of AGI: emerging, competent, expert, virtuoso, and superhuman. For example, a competent AGI is defined as an AI that outperforms 50% of skilled adults in a wide range of non-physical tasks, and a superhuman AGI (i.e., an artificial superintelligence) is similarly defined but with a threshold of 100%. They consider large language models like ChatGPT or LLaMA 2 to be instances of emerging AGI (comparable to unskilled humans). Regarding the autonomy of AGI and associated risks, they define five levels: tool (fully in human control), consultant, collaborator, expert, and agent (fully autonomous). == Characteristics == There is no single agreed-upon definition of intelligence as applied to computers. Computer scientist John McCarthy wrote in 2007: "We cannot yet characterize in general what kinds of computational procedures we want to call intelligent." === Intelligence traits === Researchers generally hold that a system is required to do all of the following to be regarded as an AGI: reason, use strategy, solve puzzles, and make judgments under uncertainty, represent knowledge, including common sense knowledge, plan, learn, communicate in natural language, if necessary, integrate these skills in completion of any given goal. Many interdisciplinary approaches (e.g. cognitive science, computational intelligence, and decision making) consider additional traits such as imagination (the ability to form novel mental images and concepts) and autonomy. Computer-based systems exhibiting these capabilities are now widespread, with modern large language models demonstrating computational creativity, automated reasoning, and decision support simultaneously across domains. === Physical traits === Other capabilities are considered desirable in intelligent systems, as they may affect intelligence or aid in its expression. These include: the ability to sense (e.g. see, hear, etc.), and the ability to act (e.g. move and manipulate objects, change location to explore, etc.) This includes the ability to detect and respond to hazard. === Tests for human-level AGI === Several tests meant to confirm human-level AGI have been considered. ==== Turing test ==== The Turing test was proposed by Alan Turing in his 1950 paper "Computing Machinery and Intelligence". This test involves a human judge engaging in natural language conversations with both a human and a machine designed to generate human-like responses. The machine passes the test if it can convince the judge that it is human a significant fraction of the time. Turing proposed this as a practical measure of machine intelligence, focusing on the ability to produce human-like responses rather than on the internal workings of the machine. The idea of the test is that the machine has to try and pretend to be a man, by answering questions put to it, and it will only pass if the pretence is reasonably convincing. A considerable portion of a jury, who should not be experts about machines, must be taken in by the pretence. In 2014, a chatbot named Eugene Goostman, designed to imitate a 13-year-old Ukrainian boy, reportedly passed a Turing Test event by convincing 33% of judges that it was human. However, this claim was met with significant skepticism from the AI research community, who questioned the test's implementation and its relevance to AGI. A 2025 pre‑registered, three‑party Turing‑test study by Cameron R. Jones and Benjamin K. Bergen showed that GPT-4.5 was judged to be the human in 73% of five‑minute text conversations—surpassing the 67% humanness rate of real confederates and meeting the researchers' criterion for having passed the test. ==== Ikea test ==== The "Ikea test", also known as the Flat Pack Furniture Test, involves an AI controlling a robot which attempts to assemble an Ikea flat-pack furniture product after having been shown the parts and instructions. As early as 2013, MIT's IkeaBot demonstrated fully autonomous multi-robot assembly of an IKEA Lack table in ten minutes, with no human intervention and no pre-programmed assembly instructions. The robots inferred the assembly sequence from the geometry of the parts alone. ==== Coffee test ==== Steve Wozniak proposed a test where a machine is required to enter an average American home and figure out how to make coffee. It must find the coffee machine, find the coffee, add water, find a mug, and brew the coffee by pushing the proper buttons. This test has been substantially approached across multiple systems. In January 2024, Figure AI's Figure 01 humanoid learned to operate a Keurig coffee machine autonomously after watching video demonstrations, using end-to-end neural networks to translate visual input into motor actions. In 2025, researchers at the University of Edinburgh published the ELLMER framework in Nature Machine Intelligence, demonstrating a robotic arm that interprets verbal instructions, analyses its surroundings, and autonomously makes coffee in dynamic kitchen environments — adapting to unforeseen obstacles in real time rather than following pre-programmed sequences. ==== Suleyman's test ==== Mustafa Suleyman's test proposes giving an AI model US$100,000 and asking it to obtain US$1 million. ==== Use of video-games ==== Adams, et al. propose that the ability to learn and succeed in a wide range of video games can be used to test AI intelligence. This range would include games unknown to the AGI developers before the test is administered. === AI-complete problems === A problem is informally called "AI-complete" or "AI-hard" if it is believed that AGI would be needed to solve it, because the solution is beyond the capabilities of a purpose-specific algorithm. == History == === Classical AI === Modern AI research began in the mid-1950s. The first generation of AI researchers were convinced that artificial general intelligence was possible and that it would exist in just a few decades. AI pioneer Herbert A. Simon wrote in 1965: "machines will be capable, within twenty years, of doing any work a man can do". Their predictions were the inspiration for Stanley Kubrick and Arthur C. Clarke's fictional character HAL 9000, who embodied what AI researchers believed they could create by the year 2001. AI pioneer Marvin Minsky was a consultant on the project of making HAL 9000 as realistic as possible according to the consensus predictions of the time. He said in 1967, "Within a generation... the problem of
Emotion recognition
Emotion recognition is the process of identifying human emotion. People vary widely in their accuracy at recognizing the emotions of others. Use of technology to help people with emotion recognition is a relatively nascent research area. Generally, the technology works best if it uses multiple modalities in context. To date, the most work has been conducted on automating the recognition of facial expressions from video, spoken expressions from audio, written expressions from text, and physiology as measured by wearables. == Human == Humans show a great deal of variability in their abilities to recognize emotion. A key point to keep in mind when learning about automated emotion recognition is that there are several sources of "ground truth", or truth about what the real emotion is. Suppose we are trying to recognize the emotions of Alex. One source is "what would most people say that Alex is feeling?" In this case, the 'truth' may not correspond to what Alex feels, but may correspond to what most people would say it looks like Alex feels. For example, Alex may actually feel sad, but he puts on a big smile and then most people say he looks happy. If an automated method achieves the same results as a group of observers it may be considered accurate, even if it does not actually measure what Alex truly feels. Another source of 'truth' is to ask Alex what he truly feels. This works if Alex has a good sense of his internal state, and wants to tell you what it is, and is capable of putting it accurately into words or a number. However, some people are alexithymic and do not have a good sense of their internal feelings, or they are not able to communicate them accurately with words and numbers. In general, getting to the truth of what emotion is actually present can take some work, can vary depending on the criteria that are selected, and will usually involve maintaining some level of uncertainty. == Automatic == Decades of scientific research have been conducted developing and evaluating methods for automated emotion recognition. There is now an extensive literature proposing and evaluating hundreds of different kinds of methods, leveraging techniques from multiple areas, such as signal processing, machine learning, computer vision, and speech processing. Different methodologies and techniques may be employed to interpret emotion such as Bayesian networks. , Gaussian Mixture models and Hidden Markov Models and deep neural networks. === Approaches === The accuracy of emotion recognition is usually improved when it combines the analysis of human expressions from multimodal forms such as texts, physiology, audio, or video. Different emotion types are detected through the integration of information from facial expressions, body movement and gestures, and speech. The technology is said to contribute in the emergence of the so-called emotional or emotive Internet. The existing approaches in emotion recognition to classify certain emotion types can be generally classified into three main categories: knowledge-based techniques, statistical methods, and hybrid approaches. ==== Knowledge-based techniques ==== Knowledge-based techniques (sometimes referred to as lexicon-based techniques), utilize domain knowledge and the semantic and syntactic characteristics of text and potentially spoken language in order to detect certain emotion types. In this approach, it is common to use knowledge-based resources during the emotion classification process such as WordNet, SenticNet, ConceptNet, and EmotiNet, to name a few. One of the advantages of this approach is the accessibility and economy brought about by the large availability of such knowledge-based resources. A limitation of this technique on the other hand, is its inability to handle concept nuances and complex linguistic rules. Knowledge-based techniques can be mainly classified into two categories: dictionary-based and corpus-based approaches. Dictionary-based approaches find opinion or emotion seed words in a dictionary and search for their synonyms and antonyms to expand the initial list of opinions or emotions. Corpus-based approaches on the other hand, start with a seed list of opinion or emotion words, and expand the database by finding other words with context-specific characteristics in a large corpus. While corpus-based approaches take into account context, their performance still vary in different domains since a word in one domain can have a different orientation in another domain. ==== Statistical methods ==== Statistical methods commonly involve the use of different supervised machine learning algorithms in which a large set of annotated data is fed into the algorithms for the system to learn and predict the appropriate emotion types. Machine learning algorithms generally provide more reasonable classification accuracy compared to other approaches, but one of the challenges in achieving good results in the classification process, is the need to have a sufficiently large training set. Some of the most commonly used machine learning algorithms include Support Vector Machines (SVM), Naive Bayes, and Maximum Entropy. Deep learning, which is under the unsupervised family of machine learning, is also widely employed in emotion recognition. Well-known deep learning algorithms include different architectures of Artificial Neural Network (ANN) such as Convolutional Neural Network (CNN), Long Short-term Memory (LSTM), and Extreme Learning Machine (ELM). The popularity of deep learning approaches in the domain of emotion recognition may be mainly attributed to its success in related applications such as in computer vision, speech recognition, and Natural Language Processing (NLP). ==== Hybrid approaches ==== Hybrid approaches in emotion recognition are essentially a combination of knowledge-based techniques and statistical methods, which exploit complementary characteristics from both techniques. Some of the works that have applied an ensemble of knowledge-driven linguistic elements and statistical methods include sentic computing and iFeel, both of which have adopted the concept-level knowledge-based resource SenticNet. The role of such knowledge-based resources in the implementation of hybrid approaches is highly important in the emotion classification process. Since hybrid techniques gain from the benefits offered by both knowledge-based and statistical approaches, they tend to have better classification performance as opposed to employing knowledge-based or statistical methods independently. A downside of using hybrid techniques however, is the computational complexity during the classification process. === Datasets === Data is an integral part of the existing approaches in emotion recognition and in most cases it is a challenge to obtain annotated data that is necessary to train machine learning algorithms. For the task of classifying different emotion types from multimodal sources in the form of texts, audio, videos or physiological signals, the following datasets are available: HUMAINE: provides natural clips with emotion words and context labels in multiple modalities Belfast database: provides clips with a wide range of emotions from TV programs and interview recordings SEMAINE: provides audiovisual recordings between a person and a virtual agent and contains emotion annotations such as angry, happy, fear, disgust, sadness, contempt, and amusement IEMOCAP: provides recordings of dyadic sessions between actors and contains emotion annotations such as happiness, anger, sadness, frustration, and neutral state eNTERFACE: provides audiovisual recordings of subjects from seven nationalities and contains emotion annotations such as happiness, anger, sadness, surprise, disgust, and fear DEAP: provides electroencephalography (EEG), electrocardiography (ECG), and face video recordings, as well as emotion annotations in terms of valence, arousal, and dominance of people watching film clips DREAMER: provides electroencephalography (EEG) and electrocardiography (ECG) recordings, as well as emotion annotations in terms of valence, dominance of people watching film clips MELD: is a multiparty conversational dataset where each utterance is labeled with emotion and sentiment. MELD provides conversations in video format and hence suitable for multimodal emotion recognition and sentiment analysis. MELD is useful for multimodal sentiment analysis and emotion recognition, dialogue systems and emotion recognition in conversations. MuSe: provides audiovisual recordings of natural interactions between a person and an object. It has discrete and continuous emotion annotations in terms of valence, arousal and trustworthiness as well as speech topics useful for multimodal sentiment analysis and emotion recognition. UIT-VSMEC: is a standard Vietnamese Social Media Emotion Corpus (UIT-VSMEC) with about 6,927 human-annotated sentences with six emotion labels, contributing to emotion recognition research in Vietnamese