AI Chat Interface

AI Chat Interface — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

  • Niki.ai

    Niki.ai

    Niki was an artificial intelligence company headquartered in Bangalore, Karnataka. It was founded in May 2015 by IIT Kharagpur graduates Sachin Jaiswal, Keshav Prawasi, Shishir Modi, and Nitin Babel. The Niki android app was launched for a limited beta in June 2015, then released for public during YourStory's TechSparks 2015, and is a Tech30 company. The company raised an undisclosed amount in seed funding from Unilazer Ventures, a Mumbai-based VC firm founded by Ronnie Screwvala, in October 2015. This was followed by another seed funding round by Ratan Tata in May 2016. The company then raised US$2 million in Series A round of funding from SAP.iO, existing investors and some US and German-based investors, among others. Niki.ai shut down in October 2021 as per media reports. Website not working. == Product == The product is an artificial intelligence-powered chatbot which works as an intelligent personal assistant, named Niki. Leveraging natural language processing and machine learning, Niki presents a chat-based natural language user interface to the users where they can interact with Niki in their natural language. Niki understands how users chat in India, deciphers the words, in the context of product/services that they would like to purchase, and comes up with apt recommendations. Initially, it was only available on the Android platform as a mobile app. The company has expanded its operations to the Facebook Messenger and Apple iOS platforms. The company aims to soon be present on more messaging platforms like Slack and WhatsApp. The company currently provides 20+ services to over 2 million consumers, covering a wide spectrum ranging from utility services like mobile recharge, bill payments, travel services like cabs, buses, hotels and entertainment services like movies and events. Services such as flights and healthcare are also planned. == Partnerships == In September 2017, Infosys Finacle joined with Niki.ai to provide chat-based service to banking customers. In August 2017, Niki partnered with LazyPay to enable a 'buy now, pay later' feature for its users.

    Read more →
  • Ballie

    Ballie

    Ballie is an AI robot created by Samsung to be released in 2026. It is an autonomous robot which has the ability to control smart home devices. Ballie can text, send pictures and follow commands through SmartThings. It can also show workout information shared from a Galaxy Watch. Ballie can make video calls and welcome you home. == History == It was first unveiled at Samsung's CES event in CES 2020, and later updated the design in CES 2024, and will be later released in 2026. == Design ==

    Read more →
  • Zvi Mowshowitz

    Zvi Mowshowitz

    Zvi Mowshowitz is an American writer and member of the rationalist community who primarily discusses new developments in artificial intelligence. He is a former competitive Magic: The Gathering player and was CEO of MetaMed. == Career == Mowshowitz is an alumnus of Columbia University and holds a bachelor's degree in mathematics. He co-founded and was the CEO of MetaMed, a medical research analysis firm. He has worked at Jane Street Capital, and has worked for the gambling industry in Las Vegas. He attempted to launch a blockchain game, Emergents, in 2020. === Magic: The Gathering === Mowshowitz held a developer intern position at Wizards of the Coast R&D in 2005. He created the deck TurboZvi. His first-place finishes at major competitions were the 1999 World Championships as part of the four-person United States national team, the 2001 Pro Tour Tokyo, and two 2003 Grand Prix. He has placed in the top eight of four Pro Tours, and earned over $140,000 playing Magic competitively. In 2007, Mowshowitz was elected into the Magic Hall of Fame. Last updated: 12 May 2013Source: Wizards.com Mowshowitz has written about Magic for several outlets, including the official Magic website. === Later career === Mowshowitz is on the board of directors for the Center for Applied Rationality, and is a member of the rationalist community. He also founded Balsa Research, a nonprofit think tank which advocated for the repeal of the Jones Act, increasing the housing supply, and reform of the National Environmental Policy Act. In 2023, Mowshowitz wrote an article for Vox on the topic of artificial intelligence safety. Mowshowitz has a blog on Substack under the name "Don't Worry about the Vase". He has written on topics such as artificial intelligence, economics, and the COVID-19 pandemic. == Personal life == Mowshowitz is the son of American biochemist Deborah Mowshowitz. His parents have both worked as Columbia University professors.

    Read more →
  • Meta Content Framework

    Meta Content Framework

    Meta Content Framework (MCF) is a specification of a content format for structuring metadata about web sites and other data. == History == MCF was developed by Ramanathan V. Guha at Apple Computer's Advanced Technology Group between 1995 and 1997. Rooted in knowledge-representation systems such as CycL, KRL, and KIF, it sought to describe objects, their attributes, and the relationships between them. One application of MCF was HotSauce, also developed by Guha while at Apple. It generated a 3D visualization of a web site's table of contents, based on MCF descriptions. By late 1996, a few hundred sites were creating MCF files and Apple HotSauce allowed users to browse these MCF representations in 3D. When the research project was discontinued, Guha left Apple for Netscape, where, in collaboration with Tim Bray, he adapted MCF to use XML and created the first version of the Resource Description Framework (RDF). == MCF format == An MCF file consists of one or more blocks, each corresponding to an entity. A block looks like this:The identifier is a unique identifier for that entity (more on the scope of the identifier below) and is used to refer to that entity. The following lines each specify a property and one or more values, separated by commas. Each value can be a reference to another entity (via its identifier), a string (enclosed by double quotes) or a number. For example:NOTE: The identifier must not include a comma (,) and must not be enclosed within double quotes. A common parsing failure is due to odd number of unescaped double quotes in text. For instance, "foo bar" baz" needs to be "foo bar\" baz". Commas within double quotes are not considered as value separators. Every entity has at least one property: typeOf.

    Read more →
  • Inferential theory of learning

    Inferential theory of learning

    Inferential Theory of Learning (ITL) is an area of machine learning which describes inferential processes performed by learning agents. ITL has been continuously developed by Ryszard S. Michalski, starting in the 1980s. The first known publication of ITL was in 1983. In the ITL learning process is viewed as a search (inference) through hypotheses space guided by a specific goal. The results of learning need to be stored. Stored information will later be used by the learner for future inferences. Inferences are split into multiple categories including conclusive, deduction, and induction. In order for an inference to be considered complete it was required that all categories must be taken into account. This is how the ITL varies from other machine learning theories like Computational Learning Theory and Statistical Learning Theory; which both use singular forms of inference. == Usage == The most relevant published usage of ITL was in scientific journal published in 2012 and used ITL as a way to describe how agent-based learning works. According to the journal "The Inferential Theory of Learning (ITL) provides an elegant way of describing learning processes by agents".

    Read more →
  • Project Maven

    Project Maven

    Project Maven (officially Algorithmic Warfare Cross Functional Team) is a United States Department of Defense initiative launched in 2017 to accelerate the adoption of machine learning and data integration across U.S. military intelligence workflows, specifically in intelligence, surveillance, target acquisition, and reconnaissance as well as in geospatial intelligence. It initially focused on applying computer vision for processing images and videos for intelligence purposes. Currently, the program operates under the National Geospatial-Intelligence Agency (NGA) and encompasses multiple applications across the Department of Defense spanning military operation targeting support, data integration and visualization for analysts, and training machine learning models on labeled datasets of military assets and infrastructure. It integrates data from drones, satellites, and other sensors to flag potential targets, present findings to human analysts, and relay their decisions to operational systems. The program originated under Deputy Secretary Robert O. Work after he raised concerns about China's advances in defense applications of artificial intelligence. Project leaders, Colonel Drew Cukor, USMC, and Lt. Gen. Jack Shanahan, framed the program as human-in-the-loop decision support inside the Department of Defense rather than as an autonomous weapons platform. Contractors supporting Maven have included Google, which withdrew in 2018 after internal protests, and follow-on integrators such as Palantir, Anduril, Amazon Web Services, and Anthropic (withdrew in 2026). The Pentagon credits Maven with providing 2024 targeting support for U.S. airstrikes in Iraq, Syria, and Yemen, along with locating hostile maritime assets in the Red Sea. == Administrative history == Initially, the effort was led by Robert O. Work who was concerned about China's military use of the emerging technology. Reportedly, Pentagon development stops short of acting as an AI weapons system capable of firing on self-designated targets. The project was established in a memo by the U.S. Deputy Secretary of Defense on 26 April 2017 proposing an "Algorithmic Warfare Cross-Functional Team". With the help of Defense Innovation Unit, the project obtained the support of top talents in AI outside of the traditional defense contracting base. It was initially funded for $70 million. Jack Shanahan was the director of the project during April 2017 to December 2018. At the second Defense One Tech Summit in July 2017, Cukor said that the investment in a "deliberate workflow process" was funded by the Department [of Defense] through its "rapid acquisition authorities" for about "the next 36 months". In the defense industry, the standard procedure for the military to acquire hardware is by way of research, development, test, and evaluation (RDT&E), followed by production and sustainment. In 2017, acquiring software was done in the same way as hardware. This created a problem, since software is constantly updated. Project Maven procured software using Broad Agency Announcements, a flexible contracting vehicle that categorized software as consistently RDT&E, allowing constant updating. Another issue was that the government usually acquired the intellectual property (IP) for procured software, and with the project, only parts of the IP of the software was acquired. Cukor used the principle of "platform IP belongs to the vendor, configurations on top are the customer's". For example, Palantir retained IP to their core platform, while the government obtained the IP to Maven-specific logic configured on top of it. According to US Air Force Lt. Gen. Jack Shanahan in November 2017, it is "designed to be that pilot project, that pathfinder, that spark that kindles the flame front of artificial intelligence across the rest of the [Defense] Department". Its chief, U.S. Marine Corps Col. Drew Cukor, said: "People and computers will work symbiotically to increase the ability of weapon systems to detect objects." Project Maven has been noted by allies, such as Australia's Ian Langford, for the ability to identify adversaries by harvesting data from sensors on UAVs and satellites. As of 2017 December, 150,000 images had been manually labelled to establish the first training data sets, and it was projected to reach one million by January 2018. Project Maven was funded for $221 million in fiscal 2020. In 2020, the House and Senate conferees on the National Defense Authorization Act for Fiscal Year 2021, agreed to the Senate's recommendation to fund the Pentagon's $250 million request for Project Maven. At the GEOINT Symposium of 2022, it was announced that Project Maven was transferred from the Office of the Under Secretary of Defense for Intelligence and Security to the NGA, under President Biden’s proposed budget for Fiscal Year 2023. It became a Program of Record on 2023 November 7. Frank "Trey" Whitworth, vice admiral, was the director of NGA from June 2022 to November 2025. Whitworth was initially skeptical of the program, suspecting it was incautious about the targeting principles, but later regarded it as "important work". As of 2024, the project is jointly administered by the NGA and the CDAO, and its director is Rachel Martin. Before 2025, Biden appointees within CDAO had held back AI development for safety and reliability concerns, though as of 2025, this has stopped. As of 2024, Maven provided the cloud infrastructure, software capabilities, and AI for CDAO's Combined Joint All-Domain Command and Control initiatives. As of summer 2025, there were eight Maven initiatives. Of these, five were in the NGA, including analyzing drone feeds and satellite imagery. On 18 September 2025, the UK government announced a new partnership with Palantir to develop AI-powered military capabilities for decision-making and targeting, identifying opportunities worth up to £750 million over five years. On 25 March 2025, the NATO Communications and Information Agency and Palantir finalized the acquisition of the Palantir Maven Smart System NATO (MSS NATO) for employment within NATO's Allied Command Operations. It was planned to be used within 30 days of acquisition. In a letter to Pentagon on 9 March 2026, Steve Feinberg stated that Project Maven will become an official program of record by September 2026, the close of the current fiscal year. The project would transfer from the NGA to the CDAO within 30 days. Future contracting with Palantir would be handled by the US Army. In 2026-03, it was announced that the US Army Combined Arms Command would integrate Maven into its training. == Technology == Project Maven uses machine learning algorithms to analyze and fuse vast amounts of surveillance data from multiple sources made possible through data integration using Palantir Technologies. The data sources include photographs, satellite imagery, geolocation data (IP address, geotag, metadata, etc) from communications intercepts, infrared sensors, synthetic-aperture radar, and more. The system is mainly used for assisting analysts in intelligence, surveillance, target acquisition, and reconnaissance. Machine learning systems, including object recognition systems, process the data and identify potential targets, such as enemy tanks or location of new military facility. The training dataset included at least 4 million images of military objects such as warships, labelled by humans. The user interface is called Maven Smart System. It could display information such as aircraft movements, logistics, locations of key personnel, locations on the no-strike list, ships, etc. Yellow-outlined boxes show potential targets. Blue-outlined boxes show friendly forces or no-strike zones. It could also transmit, directly to weapons, a human decision to fire weapons. Internal documentation referred to "Maven ATR: automatic target recognition". Initially the project focused on applications of computer vision. The project's leaders were particularly impressed by model performance on ImageNet. As of 2018, the purpose of the system was AI-enabled analysis of full-motion video. In 2022 it expanded to combatant commands under the AI and Data Acceleration Initiative. In 2022, it was reported that the project expanded to non-image data, including captured enemy material, maritime intelligence, and publicly available information. In 2024, it was stated that Maven's key technical contribution was data management: Maven standardizes heterogeneous data through an ontology layer so data can be fused, exchanged across cloud and edge systems, and used by multiple applications. The system was presented as a broader data-centric warfighting system that feeds apps for planning, preparing, and executing operations. In 2024, the Broad Area Surveillance-Targeting (BAS-T) is a part of Maven. The system detects objects in images and uses data fusion to produce a common operational picture containing "priority based, in-depth assessment of the enemy systems pre

    Read more →
  • Semantic triple

    Semantic triple

    A semantic triple, or RDF triple or simply triple, is the atomic data entity in the Resource Description Framework (RDF) data model. As its name indicates, a triple is a sequence of three entities that codifies a statement about semantic data in the form of subject–predicate–object expressions (e.g., "Bob is 35", or "Bob knows John"). == Subject, predicate and object == This format enables knowledge to be represented in a machine-readable way. Particularly, every part of an RDF triple is individually addressable via unique URIs—for example, the statement "Bob knows John" might be represented in RDF as: http://example.name#BobSmith12 http://xmlns.com/foaf/spec/#term_knows http://example.name#JohnDoe34. Given this precise representation, semantic data can be unambiguously queried and reasoned about. The components of a triple, such as the statement "The sky has the color blue", consist of a subject ("the sky"), a predicate ("has the color"), and an object ("blue"). This is similar to the classical notation of an entity–attribute–value model within object-oriented design, where this example would be expressed as an entity (sky), an attribute (color) and a value (blue). From this basic structure, triples can be composed into more complex models, by using triples as objects or subjects of other triples—for example, Mike → said → (triples → can be → objects). Given their particular, consistent structure, a collection of triples is often stored in purpose-built databases called triplestores. == Difference from relational databases == A relational database is the classical form for information storage, working with different tables, which consist of rows. The query language SQL is able to retrieve information from such a database. In contrast, RDF triple storage works with logical predicates. No tables nor rows are needed, but the information is stored in a text file. An RDF-triple store can be converted into an SQL database and the other way around. If the knowledge is highly unstructured and dedicated tables aren't flexible enough, semantic triples are used over classic relational storage. In contrast to a traditional SQL database, an RDF triple store isn't created with a table editor. The preferred tool is a knowledge editor, for example Protégé. Protégé looks similar to an object-oriented modeling application used for software engineering, but it's focused on natural language information. The RDF triples are aggregated into a knowledge base, which allows external parsers to run requests. Possible applications include the creation of non-player characters within video games. == Limitations == One concern about triple storage is its lack of database scalability. This problem is especially pertinent if millions of triples are stored and retrieved in a database. The seek time is larger than for classical SQL-based databases. A more complex issue is a knowledge model's inability to predict future states. Even if all the domain knowledge is available as logical predicates, the model fails in answering what-if questions. For example, suppose in the RDF format a room with a robot and table is described. The robot knows what the location of the table is, is aware of the distance to the table and knows also that a table is a type of furniture. Before the robot can plan its next action, it needs temporal reasoning capabilities. Thus, the knowledge model should answer hypothetical questions in advance before an action is taken.

    Read more →
  • AlphaGo

    AlphaGo

    AlphaGo is a computer program that plays the board game Go. It was developed by the London-based DeepMind Technologies, an acquired subsidiary of Google. Subsequent versions of AlphaGo became increasingly powerful, including a version that competed under the name Master. After retiring from competitive play, AlphaGo Master was succeeded by an even more powerful version known as AlphaGo Zero, which was completely self-taught without learning from human games. AlphaGo Zero was then generalized into a program known as AlphaZero, which played additional games, including chess and shogi. AlphaZero has in turn been succeeded by a program known as MuZero which learns without being taught the rules. AlphaGo and its successors use a Monte Carlo tree search algorithm to find its moves based on knowledge previously acquired by machine learning, specifically by an artificial neural network (a deep learning method) by extensive training, both from human and computer play. A neural network is trained to identify the best moves and the winning percentages of these moves. This neural network improves the strength of the tree search, resulting in stronger move selection in the next iteration. In October 2015, in a match against Fan Hui, the original AlphaGo became the first computer Go program to beat a human professional Go player without handicap on a full-sized 19×19 board. In March 2016, it beat Lee Sedol in a five-game match, the first time a computer Go program has beaten a 9-dan professional without handicap. Although it lost to Lee Sedol in the fourth game, Lee resigned in the final game, giving a final score of 4 games to 1 in favour of AlphaGo. In recognition of the victory, AlphaGo was awarded an honorary 9-dan by the Korea Baduk Association. The lead up and the challenge match with Lee Sedol were documented in a documentary film also titled AlphaGo, directed by Greg Kohs. The win by AlphaGo was chosen by Science as one of the Breakthrough of the Year runners-up on 22 December 2016. At the 2017 Future of Go Summit, the Master version of AlphaGo beat Ke Jie, the number one ranked player in the world at the time, in a three-game match, after which AlphaGo was awarded professional 9-dan by the Chinese Weiqi Association. After the match between AlphaGo and Ke Jie, DeepMind retired AlphaGo, while continuing AI research in other areas. The self-taught AlphaGo Zero achieved a 100–0 victory against the early competitive version of AlphaGo, and its successor AlphaZero was perceived as the world's top player in Go by the end of the 2010s. == History == Go is considered much more difficult for computers to win than other games such as chess, because its strategic and aesthetic nature makes it hard to directly construct an evaluation function, and its much larger branching factor makes it prohibitively difficult to use traditional AI methods such as alpha–beta pruning, tree traversal and heuristic search. Almost two decades after IBM's computer Deep Blue beat world chess champion Garry Kasparov in the 1997 match, the strongest Go programs using artificial intelligence techniques only reached about amateur 5-dan level, and still could not beat a professional Go player without a handicap. In 2012, the software program Zen, running on a four PC cluster, beat Masaki Takemiya (9p) twice at five- and four-stone handicaps. In 2013, Crazy Stone beat Yoshio Ishida (9p) at a four-stone handicap. According to DeepMind's David Silver, the AlphaGo research project was formed around 2014 to test how well a neural network using deep learning can compete at Go. AlphaGo represents a significant improvement over previous Go programs. In 500 games against other available Go programs, including Crazy Stone and Zen, AlphaGo running on a single computer won all but one. In a similar matchup, AlphaGo running on multiple computers won all 500 games played against other Go programs, and 77% of games played against AlphaGo running on a single computer. The distributed version in October 2015 was using 1,202 CPUs and 176 GPUs. === Match against Fan Hui === In October 2015, the distributed version of AlphaGo defeated the European Go champion Fan Hui, a 2-dan (out of 9 dan possible) professional, five to zero. This was the first time a computer Go program had beaten a professional human player on a full-sized board without handicap. The announcement of the news was delayed until 27 January 2016 to coincide with the publication of a paper in the journal Nature describing the algorithms used. === Match against Lee Sedol === AlphaGo played South Korean professional Go player Lee Sedol, ranked 9-dan, one of the best players at Go, with five games taking place at the Four Seasons Hotel in Seoul, South Korea on 9, 10, 12, 13, and 15 March 2016, which were video-streamed live. Out of five games, AlphaGo won four games and Lee won the fourth game which made him recorded as the only human player who beat AlphaGo in all of its 74 official games. AlphaGo ran on Google's cloud computing with its servers located in the United States. The match used Chinese rules with a 7.5-point komi, and each side had two hours of thinking time plus three 60-second byoyomi periods. The version of AlphaGo playing against Lee used a similar amount of computing power as was used in the Fan Hui match. The Economist reported that it used 1,920 CPUs and 280 GPUs. At the time of play, Lee Sedol had the second-highest number of Go international championship victories in the world after South Korean player Lee Chang-ho who kept the world championship title for 16 years. Since there is no single official method of ranking in international Go, the rankings may vary among the sources. While he was ranked top sometimes, some sources ranked Lee Sedol as the fourth-best player in the world at the time. AlphaGo was not specifically trained to face Lee nor was designed to compete with any specific human players. The first three games were won by AlphaGo following resignations by Lee. However, Lee beat AlphaGo in the fourth game, winning by resignation at move 180. AlphaGo then continued to achieve a fourth win, winning the fifth game by resignation. The prize was US$1 million. Since AlphaGo won four out of five and thus the series, the prize will be donated to charities, including UNICEF. Lee Sedol received $150,000 for participating in all five games and an additional $20,000 for his win in Game 4. In June 2016, at a presentation held at a university in the Netherlands, Aja Huang, one of the Deep Mind team, revealed that they had patched the logical weakness that occurred during the 4th game of the match between AlphaGo and Lee, and that after move 78 (which was dubbed the "divine move" by many professionals), it would play as intended and maintain Black's advantage. Before move 78, AlphaGo was leading throughout the game, but Lee's move caused the program's computing powers to be diverted and confused. Huang explained that AlphaGo's policy network of finding the most accurate move order and continuation did not precisely guide AlphaGo to make the correct continuation after move 78, since its value network did not determine Lee's 78th move as being the most likely, and therefore when the move was made AlphaGo could not make the right adjustment to the logical continuation. === Sixty online games === On 29 December 2016, a new account on the Tygem server named "Magister" (shown as 'Magist' at the server's Chinese version) from South Korea began to play games with professional players. It changed its account name to "Master" on 30 December, then moved to the FoxGo server on 1 January 2017. On 4 January, DeepMind confirmed that the "Magister" and the "Master" were both played by an updated version of AlphaGo, called AlphaGo Master. As of 5 January 2017, AlphaGo Master's online record was 60 wins and 0 losses, including three victories over Go's top-ranked player, Ke Jie, who had been quietly briefed in advance that Master was a version of AlphaGo. After losing to Master, Gu Li offered a bounty of 100,000 yuan (US$14,400) to the first human player who could defeat Master. Master played at the pace of 10 games per day. Many quickly suspected it to be an AI player due to little or no resting between games. Its adversaries included many world champions such as Ke Jie, Park Jeong-hwan, Yuta Iyama, Tuo Jiaxi, Mi Yuting, Shi Yue, Chen Yaoye, Li Qincheng, Gu Li, Chang Hao, Tang Weixing, Fan Tingyu, Zhou Ruiyang, Jiang Weijie, Chou Chun-hsun, Kim Ji-seok, Kang Dong-yun, Park Yeong-hun, and Won Seong-jin; national champions or world championship runners-up such as Lian Xiao, Tan Xiao, Meng Tailing, Dang Yifei, Huang Yunsong, Yang Dingxin, Gu Zihao, Shin Jinseo, Cho Han-seung, and An Sungjoon. All 60 games except one were fast-paced games with three 20 or 30 seconds byo-yomi. Master offered to extend the byo-yomi to one minute when playing with Nie Weiping in consideration of his age. After winning its 59th game Master revealed itse

    Read more →
  • Text normalization

    Text normalization

    Text normalization is the process of transforming text into a single canonical form that it might not have had before. Normalizing text before storing or processing it allows for separation of concerns, since input is guaranteed to be consistent before operations are performed on it. Text normalization requires being aware of what type of text is to be normalized and how it is to be processed afterwards; there is no all-purpose normalization procedure. == Applications == Text normalization is frequently used when converting text to speech. Numbers, dates, acronyms, and abbreviations are non-standard "words" that need to be pronounced differently depending on context. For example: "$200" would be pronounced as "two hundred dollars" in English, but as "lua selau tālā" in Samoan. "vi" could be pronounced as "vie," "vee," or "the sixth" depending on the surrounding words. Text can also be normalized for storing and searching in a database. For instance, if a search for "resume" is to match the word "résumé," then the text would be normalized by removing diacritical marks; and if "john" is to match "John", the text would be converted to a single case. To prepare text for searching, it might also be stemmed (e.g. converting "flew" and "flying" both into "fly"), canonicalized (e.g. consistently using American or British English spelling), or have stop words removed. == Techniques == For simple, context-independent normalization, such as removing non-alphanumeric characters or diacritical marks, regular expressions would suffice. For example, the sed script sed ‑e "s/\s+/ /g" inputfile would normalize runs of whitespace characters into a single space. More complex normalization requires correspondingly complicated algorithms, including domain knowledge of the language and vocabulary being normalized. Among other approaches, text normalization has been modeled as a problem of tokenizing and tagging streams of text and as a special case of machine translation. == Textual scholarship == In the field of textual scholarship and the editing of historic texts, the term "normalization" implies a degree of modernization and standardization – for example in the extension of scribal abbreviations and the transliteration of the archaic glyphs typically found in manuscript and early printed sources. A normalized edition is therefore distinguished from a diplomatic edition (or semi-diplomatic edition), in which some attempt is made to preserve these features. The aim is to strike an appropriate balance between, on the one hand, rigorous fidelity to the source text (including, for example, the preservation of enigmatic and ambiguous elements); and, on the other, producing a new text that will be comprehensible and accessible to the modern reader. The extent of normalization is therefore at the discretion of the editor, and will vary. Some editors, for example, choose to modernize archaic spellings and punctuation, but others do not. An edition of a text might be normalized based on internal criteria, where orthography is standardized according to the language of the original, or external criteria, where the norms of a different time period are applied. For an example of the latter, a published edition of a medieval Icelandic manuscript might be normalized to the conventions of modern Icelandic, or it might be normalized to Classical Old Icelandic. Standards of normalization vary based on language of the edition as well as the specific conventions of the publisher.

    Read more →
  • Texas Senate Bill 20

    Texas Senate Bill 20

    Texas Senate Bill 20 (S.B. 20), also known as the "Stopping AI-Generated Child Pornography Act", is a 2025 law in the state of Texas that creates new criminal offenses for those who possess, promote, or view visual material deemed obscene, which is said to depict a child, whether it is an actual person, animated or cartoon depiction, or an image of someone created through computer software or artificial intelligence. It was passed by the Texas Legislature on May 28, 2025, unanimously in both chambers. It was signed into law by Governor Greg Abbott on June 20, 2025. It went into effect on September 1, 2025. It was authored by Pete Flores and co-sponsored by Brent Hagenbuch, Juan Hinojosa, Joan Huffman, Phil King, and Tan Parker, as part of a package of legislation in the Texas House and Senate about A.I. and child pornography. Some supporters called it "common-sense" legislation falling within the "proper role" of government, protecting children and the "common good" within the state, with Heidi Ruiz, a police sergeant in Houston, describing the bill as "fantastic" and "fabulous." The bill drew comparisons to language, within Texas state legislation, which aimed to institute state-level book bans. Critics described the law as unconstitutional, saying it violated the Free Speech Clause of the First Amendment which prohibits abridgement of freedom of speech and the press, including the legal precedent set in Ashcroft v. Free Speech Coalition. The Comic Book Legal Defense Fund vowed to support those wrongly accused under the law. Much of the controversy regarding S.B. 20 involves the broad language pertaining to "obscene" pornographic images as including A.I.-created, animated, and cartoon depictions, with some critics arguing it could have a chilling effect on anime, manga, graphic novels, and other media produced, distributed, or created within Texas. == Provisions == S.B. 20 gives Texas police more provisions to restrict artificial intelligence-created child pornography, creating new criminal charge for possessing material depicting an underage person, under age 18, whether this child is an actual person or not. Those charged with this felony offense could go to state jail, but this could be elevated if the person charged has a prior conviction, of a $10,000 fine and two years in prison. == Reactions == === Support === Lieutenant Governor Dan Patrick applauded the unanimous passage of the law in the Texas Senate and called it "a priority" to protect children in Texas, and Texas citizens and thanked Pete Flores for his work on "this important issue". He later described the bill as part of the "bold, conservative agenda" that the Texas legislature passed during the 2025 legislative session. Phil King, one of the bill's co-sponsors, said that issue of child pornography had "infiltrated" the state's schools and said he was proud that the Texas legislature had "taken decisive action to protect our vulnerable Texans". Another co-sponsor of the legislation, Tan Parker described the law as "decisive action" to protect the children within Texas, and said he looked "forward to advancing this critical legislation" onward from the Texas Senate Criminal Justice Committee. He also described the legislation as "critical" action to protect the state's children from A.I.-generated child pornography and an "effective tool for law enforcement" to crack down on child porn perpetrators. Other supporters, such as police, and prosecutors, called the legislation an "important step" to ensure that images generated with A.I., along with deepfakes, "can't be shared with impunity" and necessary to ensure children's protection. Flores told senators that technology which enabled the production of "offensive" material by child predators had "no redeeming value whatsoever" and asserted that the materials had often been "used to groom and abuse children". John Leigh, a co-founder of Anime Matsuri, one of the largest conventions for anime within Texas, reassured those who contacted him, saying that the law is not targeted at anime and manga fans, stated that he supported the legislation, describing it as a step "in the right direction," and said that he did not believe it would "negatively impact" anime or related art in the state. Also, State Representative Dade Phelan emphasized the legislation's urgency to deal with A.I. and child pornography, adding that they need to "put some guardrails on it to where the public is being taken care of". The Texas Policy Research Foundation supported the legislation, saying that although it may lead to increased demands on state and local governmental resources, higher costs for local governments, and possible "civil liberty concerns" around online censorship, it represents a "necessary legal update" to address exploitation of children online, while "modernizing enforcement mechanisms" and recommended that lawmakers vote in favor of the law. Additionally, the group Texans for Fiscal Responsibility supported the law, arguing that it strengthened state law, upheld public safety, protected minors, and called it a "common-sense bill" protecting and promoting the "common good", children, and fell within the "proper role" of government. The Texas Public Policy Foundation also expressed their support for the law. A policy director for aforementioned conservative think tank, Zach Whiting, told the Texas Senate Committee on Criminal Justice, on March 4, 2025, that the foundation would assist legislators ans staff to "advance any and all measures to protect kids online" and shared an excerpt from of research paper about threats posed by A.I. in creating "sexually explicit deepfakes of children". === Opposition === Although the bill passed both chambers unanimously, there were some reports that the bill stalled due to opposition from Democratic lawmakers. Additionally, some individuals expressed concerns about the broad nature of the law's provisions. Anime Matsuri co-founder Deneice Leigh called for the law's wording to be clarified because "artists are anxious about displaying or selling fan art" even if the intention is "not be to penalize creators". She also described the bill as "vague and open to interpretation" as to what would be considered obscene and offensive while noting that the bill is not aiming to "target artists". Benjamin Napier, owner of Mansfield Comics and Manga in Mansfield, Texas, said that at first he felt the law was "ridiculous" and "kind of frivolous" at first, part of a "misguided puritanical onslaught", and noted that he would not cow "to the puritanical regime" if it was enacted. Kirsten Cather, an Asian Studies scholar at University of Texas, expressed concern at the law's misinterpretation because "many anime characters appear youthful, regardless of their actual age", said that the law could "stifle creative expression", and noted that the law's scope is broad enough to have manga and anime under scrutiny, a "real slippery slope here that's being breached". Marcel Green of Screen Rant said that the law's ambiguity led to concerns from manga and anime fans, and theorized that the law's application to a fan within Texas, who downloaded the 368th chapter of My Hero Academia, which has a "sexualized depiction" of an "underage high school student", would result in a criminal offense of "180 days to two years in state jail, along with a fine of up to $10,000". Green also said the law is problematic because many anime and manga characters are young, with many protagonists as minors and argued that the law could apply in limited cases, if state officials deemed an anime or manga under scrutiny as lacking "artistic value". Evan D. Mullicane, on the same site, said the vague wording of the legislation made it "dangerous" for anime such as Dragon Ball and Naruto, and could impact more than hentai, predicting it will be used against more than its "intended target" and be used to censor stories with "young LGBTQIA characters". Another critic on the same site, Carlyle Edmundson, called for anime fans to step up and prevent the law's enactment "for the good of artists and fans everywhere", saying that the legislation was "draconian" and claimed it was the most extreme case of anime and manga censorship in U.S. history. Nick Valdez of ComicBook.com said that the legislation could lead to censorship of "many anime and manga projects," like Kill la Kill and The 100 Girlfriends Who Really, Really, Really, Really, Really Love You, becoming a crime, and said that even if the law is enforced in a case-by-case basis, it could lead to a "much larger ban of materials in the state" itself due to the content of certain manga and anime. Vanessa Esguerra of The Mary Sue argued that possession of manga like Berserk and Vagabond, or viewing Dandadan, could be deemed illegal under the law, due to various parts of each of these media, and asserted that viewing and owning certain anime and other media, falling under the law's provisions,

    Read more →
  • Artificial intelligence systems integration

    Artificial intelligence systems integration

    The core idea of artificial intelligence systems integration is making individual software components, such as speech synthesizers, interoperable with other components, such as common sense knowledgebases, in order to create larger, broader and more capable A.I. systems. The main methods that have been proposed for integration are message routing, or communication protocols that the software components use to communicate with each other, often through a middleware blackboard system. Most artificial intelligence systems involve some sort of integrated technologies, for example, the integration of speech synthesis technologies with that of speech recognition. However, in recent years, there has been an increasing discussion on the importance of systems integration as a field in its own right. Proponents of this approach are researchers such as Marvin Minsky, Aaron Sloman, Deb Roy, Kristinn R. Thórisson and Michael A. Arbib. A reason for the recent attention A.I. integration is attracting is that there have already been created a number of (relatively) simple A.I. systems for specific problem domains (such as computer vision, speech synthesis, etc.), and that integrating what's already available is a more logical approach to broader A.I. than building monolithic systems from scratch. == Integration focus == The focus on systems' integration, especially with regard to modular approaches, derive from the fact that most intelligences of significant scales are composed of a multitude of processes and/or utilize multi-modal input and output. For example, a humanoid-type of intelligence would preferably have to be able to talk using speech synthesis, hear using speech recognition, understand using a logical (or some other undefined) mechanism, and so forth. In order to produce artificially intelligent software of broader intelligence, integration of these modalities is necessary. == Challenges and solutions == Collaboration is an integral part of software development as evidenced by the size of software companies and the size of their software departments. Among the tools to ease software collaboration are various procedures and standards that developers can follow to ensure quality, reliability and that their software is compatible with software created by others (such as W3C standards for webpage development). However, collaboration in fields of A.I. has been lacking, for the most part not seen outside the respected schools, departments or research institutes (and sometimes not within them either). This presents practitioners of A.I. systems integration with a substantial problem and often causes A.I. researchers to have to 're-invent the wheel' each time they want a specific functionality to work with their software. Even more damaging is the "not invented here" syndrome, which manifests itself in a strong reluctance of A.I. researchers to build on the work of others. The outcome of this in A.I. is a large set of "solution islands": A.I. research has produced numerous isolated software components and mechanisms that deal with various parts of intelligence separately. To take some examples: Speech synthesis FreeTTS from CMU Speech recognition Sphinx from CMU Logical reasoning OpenCyc from Cycorp Open Mind Common Sense Net from MIT With the increased popularity of the free software movement, a lot of the software being created, including A.I. systems, is available for public exploit. The next natural step is to merge these individual software components into coherent, intelligent systems of a broader nature. As a multitude of components (that often serve the same purpose) have already been created by the community, the most accessible way of integration is giving each of these components an easy way to communicate with each other. By doing so, each component by itself becomes a module, which can then be tried in various settings and configurations of larger architectures. Some challenging and limitations of using A.I. software is the uncontrolled fatal errors. For example, serious and fatal errors have been discovered in very precise fields such as human oncology, as in an article published in the journal Oral Oncology Reports entitled "When AI goes wrong: Fatal errors in oncological research reviewing assistance". The article pointed out a grave error in artificial intelligence based on GBT in the field of biophysics. Many online communities for A.I. developers exist where tutorials, examples, and forums aim at helping both beginners and experts build intelligent systems. However, few communities have succeeded in making a certain standard, or a code of conduct popular to allow the large collection of miscellaneous systems to be integrated with ease. == Methodologies == === Constructionist design methodology === The constructionist design methodology (CDM, or 'Constructionist A.I.') is a formal methodology proposed in 2004, for use in the development of cognitive robotics, communicative humanoids and broad AI systems. The creation of such systems requires the integration of a large number of functionalities that must be carefully coordinated to achieve coherent system behavior. CDM is based on iterative design steps that lead to the creation of a network of named interacting modules, communicating via explicitly typed streams and discrete messages. The OpenAIR message protocol (see below) was inspired by the CDM and has frequently been used to aid in the development of intelligent systems using CDM. == Examples == ASIMO, Honda's humanoid robot, and QRIO, Sony's version of a humanoid robot. Cog, M.I.T. humanoid robot project under the direction of Rodney Brooks. AIBO, Sony's robot dog, integrates vision, hearing and motorskills. TOPIO, TOSY's humanoid robot can play ping-pong with human

    Read more →
  • Partial-order planning

    Partial-order planning

    Partial-order planning is an approach to automated planning that maintains a partial ordering between actions and only commits ordering between actions when forced to, that is, ordering of actions is partial. Also this planning doesn't specify which action will come out first when two actions are processed. By contrast, total-order planning maintains a total ordering between all actions at every stage of planning. Given a problem in which some sequence of actions is needed to achieve a goal, a partial-order plan specifies all actions that must be taken, but specifies an ordering between actions only where needed. Consider the following situation: a person must travel from the start to the end of an obstacle course. The course is composed of a bridge, a see-saw, and a swing-set. The bridge must be traversed before the see-saw and swing-set are reachable. Once reachable, the see-saw and swing-set can be traversed in any order, after which the end is reachable. In a partial-order plan, ordering between these obstacles is specified only when needed. The bridge must be traversed first. Second, either the see-saw or swing-set can be traversed. Third, the remaining obstacle can be traversed. Then the end can be traversed. Partial-order planning relies upon the principle of least commitment for its efficiency. == Partial-order plan == A partial-order plan or partial plan is a plan which specifies all actions that must be taken, but only specifies the order between actions when needed. It is the result of a partial-order planner. A partial-order plan consists of four components: A set of actions (also known as operators). A partial order for the actions. It specifies the conditions about the order of some actions. A set of causal links. It specifies which actions meet which preconditions of other actions. Alternatively, a set of bindings between the variables in actions. A set of open preconditions. It specifies which preconditions are not fulfilled by any action in the partial-order plan. To keep the possible orders of the actions as open as possible, the set of order conditions and causal links must be as small as possible. A plan is a solution if the set of open preconditions is empty. A linearization of a partial order plan is a total order plan derived from the particular partial order plan; in other words, both order plans consist of the same actions, with the order in the linearization being a linear extension of the partial order in the original partial order plan. === Example === For example, a plan for baking a cake might start: go to the store get eggs; get flour; get milk pay for all goods go to the kitchen This is a partial plan because the order for finding eggs, flour and milk is not specified, the agent can wander around the store reactively accumulating all the items on its shopping list until the list is complete. == Partial-order planner == A partial-order planner is an algorithm or program which will construct a partial-order plan and search for a solution. The input is the problem description, consisting of descriptions of the initial state, the goal and possible actions. The problem can be interpreted as a search problem where the set of possible partial-order plans is the search space. The initial state would be the plan with the open preconditions equal to the goal conditions. The final state would be any plan with no open preconditions, i.e. a solution. The initial state is the starting conditions, and can be thought of as the preconditions to the task at hand. For a task of setting the table, the initial state could be a clear table. The goal is simply the final action that needs to be accomplished, for example setting the table. The operators of the algorithm are the actions by which the task is accomplished. For this example there may be two operators: lay (tablecloth), and place (glasses, plates, and silverware). === Plan space === The plan space of the algorithm is constrained between its start and finish. The algorithm starts, producing the initial state and finishes when all parts of the goal have been achieved. In the setting a table example, two types of actions exist that must be addressed: the put-out and lay operators. Four unsolved operators also exist: Action 1, lay-tablecloth, Action 2, Put-out (plates), Action 3, Put-out (silverware), and Action 4, Put-out (glasses). However, a threat arises if Action 2, 3, or 4 comes before Action 1. This threat is that the precondition to the start of the algorithm will be unsatisfied as the table will no longer be clear. Thus, constraints exist that must be added to the algorithm that force Actions 2, 3, and 4 to come after Action 1. Once these steps are completed, the algorithm will finish and the goal will have been completed. === Threats === As seen in the algorithm presented above, partial-order planning can encounter certain threats, meaning orderings that threaten to break connected actions, thus potentially destroying the entire plan. There are two ways to resolve threats: Promotion Demotion Promotion orders the possible threat after the connection it threatens. Demotion orders the possible threat before the connection it threatens. Partial-order planning algorithms are known for being both sound and complete, with sound being defined as the total ordering of the algorithm, and complete being defined as the capability to find a solution, given that a solution does in fact exist. == Partial-order vs. total-order planning == Partial-order planning is the opposite of total-order planning, in which actions are sequenced all at once and for the entirety of the task at hand. The question arises when one has two competing processes, which one is better? Anthony Barret and Daniel Weld have argued in their 1993 book, that partial-order planning is superior to total-order planning, as it is faster and thus more efficient. They tested this theory using Korf’s taxonomy of subgoal collections, in which they found that partial-order planning performs better because it produces more trivial serializability than total-order planning. Trivial serializability facilitates a planner’s ability to perform quickly when dealing with goals that contain subgoals. Planners perform more slowly when dealing with laboriously serializable or nonserializable subgoals. The determining factor that makes a subgoal trivially or laboriously serializable is the search space of different plans. They found that partial-order planning is more adept at finding the quickest path, and is therefore the more efficient of these two main types of planning. == The Sussman anomaly == Partial-order plans are known to easily and optimally solve the Sussman anomaly. Using this type of incremental planning system solves this problem quickly and efficiently. This was a result of partial-order planning that solidified its place as an efficient planning system. == Disadvantages to partial-order planning == One drawback of this type of planning system is that it requires a lot more computational power for each node. This higher per-node cost occurs because the algorithm for partial-order planning is more complex than others. This has important artificial intelligence implications. When coding a robot to do a certain task, the creator needs to take into account how much energy is needed. Though a partial-order plan may be quicker it may not be worth the energy cost for the robot. The creator must be aware of and weigh these two options to build an efficient robot.

    Read more →
  • Inductive probability

    Inductive probability

    Inductive probability attempts to give the probability of future events based on past events. It is the basis for inductive reasoning, and gives the mathematical basis for learning and the perception of patterns. It is a source of knowledge about the world. There are three sources of knowledge: inference, communication, and deduction. Communication relays information found using other methods. Deduction establishes new facts based on existing facts. Inference establishes new facts from data. Its basis is Bayes' theorem. Information describing the world is written in a language. For example, a simple mathematical language of propositions may be chosen. Sentences may be written down in this language as strings of characters. But in the computer it is possible to encode these sentences as strings of bits (1s and 0s). Then the language may be encoded so that the most commonly used sentences are the shortest. This internal language implicitly represents probabilities of statements. Occam's razor says the "simplest theory, consistent with the data is most likely to be correct". The "simplest theory" is interpreted as the representation of the theory written in this internal language. The theory with the shortest encoding in this internal language is most likely to be correct. == History == Probability and statistics was focused on probability distributions and tests of significance. Probability was formal, well defined, but limited in scope. In particular its application was limited to situations that could be defined as an experiment or trial, with a well defined population. Bayes's theorem is named after Rev. Thomas Bayes 1701–1761. Bayesian inference broadened the application of probability to many situations where a population was not well defined. But Bayes' theorem always depended on prior probabilities, to generate new probabilities. It was unclear where these prior probabilities should come from. Ray Solomonoff developed algorithmic probability which gave an explanation for what randomness is and how patterns in the data may be represented by computer programs, that give shorter representations of the data circa 1964. Chris Wallace and D. M. Boulton developed minimum message length circa 1968. Later Jorma Rissanen developed the minimum description length circa 1978. These methods allow information theory to be related to probability, in a way that can be compared to the application of Bayes' theorem, but which give a source and explanation for the role of prior probabilities. Marcus Hutter combined decision theory with the work of Ray Solomonoff and Andrey Kolmogorov to give a theory for the Pareto optimal behavior for an Intelligent agent, circa 1998. === Minimum description/message length === The program with the shortest length that matches the data is the most likely to predict future data. This is the thesis behind the minimum message length and minimum description length methods. At first sight Bayes' theorem appears different from the minimimum message/description length principle. At closer inspection it turns out to be the same. Bayes' theorem is about conditional probabilities, and states the probability that event B happens if firstly event A happens: P ( A ∧ B ) = P ( B ) ⋅ P ( A | B ) = P ( A ) ⋅ P ( B | A ) {\displaystyle P(A\land B)=P(B)\cdot P(A|B)=P(A)\cdot P(B|A)} becomes in terms of message length L, L ( A ∧ B ) = L ( B ) + L ( A | B ) = L ( A ) + L ( B | A ) . {\displaystyle L(A\land B)=L(B)+L(A|B)=L(A)+L(B|A).} This means that if all the information is given describing an event then the length of the information may be used to give the raw probability of the event. So if the information describing the occurrence of A is given, along with the information describing B given A, then all the information describing A and B has been given. ==== Overfitting ==== Overfitting occurs when the model matches the random noise and not the pattern in the data. For example, take the situation where a curve is fitted to a set of points. If a polynomial with many terms is fitted then it can more closely represent the data. Then the fit will be better, and the information needed to describe the deviations from the fitted curve will be smaller. Smaller information length means higher probability. However, the information needed to describe the curve must also be considered. The total information for a curve with many terms may be greater than for a curve with fewer terms, that has not as good a fit, but needs less information to describe the polynomial. === Inference based on program complexity === Solomonoff's theory of inductive inference is also inductive inference. A bit string x is observed. Then consider all programs that generate strings starting with x. Cast in the form of inductive inference, the programs are theories that imply the observation of the bit string x. The method used here to give probabilities for inductive inference is based on Solomonoff's theory of inductive inference. ==== Detecting patterns in the data ==== If all the bits are 1, then people infer that there is a bias in the coin and that it is more likely also that the next bit is 1 also. This is described as learning from, or detecting a pattern in the data. Such a pattern may be represented by a computer program. A short computer program may be written that produces a series of bits which are all 1. If the length of the program K is L ( K ) {\displaystyle L(K)} bits then its prior probability is, P ( K ) = 2 − L ( K ) {\displaystyle P(K)=2^{-L(K)}} The length of the shortest program that represents the string of bits is called the Kolmogorov complexity. Kolmogorov complexity is not computable. This is related to the halting problem. When searching for the shortest program some programs may go into an infinite loop. ==== Considering all theories ==== The Greek philosopher Epicurus is quoted as saying "If more than one theory is consistent with the observations, keep all theories". As in a crime novel all theories must be considered in determining the likely murderer, so with inductive probability all programs must be considered in determining the likely future bits arising from the stream of bits. Programs that are already longer than n have no predictive power. The raw (or prior) probability that the pattern of bits is random (has no pattern) is 2 − n {\displaystyle 2^{-n}} . Each program that produces the sequence of bits, but is shorter than the n is a theory/pattern about the bits with a probability of 2 − k {\displaystyle 2^{-k}} where k is the length of the program. The probability of receiving a sequence of bits y after receiving a series of bits x is then the conditional probability of receiving y given x, which is the probability of x with y appended, divided by the probability of x. ==== Universal priors ==== The programming language affects the predictions of the next bit in the string. The language acts as a prior probability. This is particularly a problem where the programming language codes for numbers and other data types. Intuitively we think that 0 and 1 are simple numbers, and that prime numbers are somehow more complex than numbers that may be composite. Using the Kolmogorov complexity gives an unbiased estimate (a universal prior) of the prior probability of a number. As a thought experiment an intelligent agent may be fitted with a data input device giving a series of numbers, after applying some transformation function to the raw numbers. Another agent might have the same input device with a different transformation function. The agents do not see or know about these transformation functions. Then there appears no rational basis for preferring one function over another. A universal prior insures that although two agents may have different initial probability distributions for the data input, the difference will be bounded by a constant. So universal priors do not eliminate an initial bias, but they reduce and limit it. Whenever we describe an event in a language, either using a natural language or other, the language has encoded in it our prior expectations. So some reliance on prior probabilities are inevitable. A problem arises where an intelligent agent's prior expectations interact with the environment to form a self reinforcing feed back loop. This is the problem of bias or prejudice. Universal priors reduce but do not eliminate this problem. === Universal artificial intelligence === The theory of universal artificial intelligence applies decision theory to inductive probabilities. The theory shows how the best actions to optimize a reward function may be chosen. The result is a theoretical model of intelligence. It is a fundamental theory of intelligence, which optimizes the agents behavior in, Exploring the environment; performing actions to get responses that broaden the agents knowledge. Competing or co-operating with another agent; games. Balancing short and long term rewards. In general no agent will always provi

    Read more →
  • OpenAI Five

    OpenAI Five

    OpenAI Five is a computer program by OpenAI that plays the five-on-five video game Dota 2. Its first public appearance occurred in 2017, where it was demonstrated in a live one-on-one game against the professional player Dendi, who lost to it. The following year, the system had advanced to the point of performing as a full team of five, and began playing against and showing the capability to defeat professional teams. By choosing a game as complex as Dota 2 to study machine learning, OpenAI thought they could more accurately capture the unpredictability and continuity seen in the real world, thus constructing more general problem-solving systems. The algorithms and code used by OpenAI Five were eventually borrowed by another neural network in development by the company, one which controlled a physical robotic hand. OpenAI Five has been compared to other similar cases of artificial intelligence (AI) playing against and defeating humans, such as AlphaStar in the video game StarCraft II, AlphaGo in the board game Go, Deep Blue in chess, and Watson on the television game show Jeopardy!. == History == Development on the algorithms used for the bots began in November 2016. OpenAI decided to use Dota 2, a competitive five-on-five video game, as a base due to it being popular on the live streaming platform Twitch, having native support for Linux, and had an application programming interface (API) available. Before becoming a team of five, the first public demonstration occurred at The International 2017 in August, the annual premiere championship tournament for the game, where Dendi, a Ukrainian professional player, lost against an OpenAI bot in a live one-on-one matchup. After the match, CTO Greg Brockman explained that the bot had learned by playing against itself for two weeks of real time, and that the learning software was a step in the direction of creating software that can handle complex tasks "like being a surgeon". OpenAI used a methodology called reinforcement learning, as the bots learn over time by playing against itself hundreds of times a day for months, in which they are rewarded for actions such as killing an enemy and destroying towers. By June 2018, the ability of the bots expanded to play together as a full team of five and were able to defeat teams of amateur and semi-professional players. At The International 2018, OpenAI Five played in two games against professional teams, one against the Brazilian-based paiN Gaming and the other against an all-star team of former Chinese players. Although the bots lost both matches, OpenAI still considered it a successful venture, stating that playing against some of the best players in Dota 2 allowed them to analyze and adjust their algorithms for future games. The bots' final public demonstration occurred in April 2019, where they won a best-of-three series against The International 2018 champions OG at a live event in San Francisco. A four-day online event to play against the bots, open to the public, occurred the same month. There, the bots played in 42,729 public games, winning 99.4% of those games. == Architecture == Each OpenAI Five bot is a neural network containing a single layer with a 4096-unit LSTM that observes the current game state extracted from the Dota developer's API. The neural network conducts actions via numerous possible action heads (no human data involved), and every head has meaning. For instance, the number of ticks to delay an action, what action to select – the X or Y coordinate of this action in a grid around the unit. In addition, action heads are computed independently. The AI system observes the world as a list of 20,000 numbers and takes an action by conducting a list of eight enumeration values. Also, it selects different actions and targets to understand how to encode every action and observe the world. OpenAI Five has been developed as a general-purpose reinforcement learning training system on the "Rapid" infrastructure. Rapid consists of two layers: it spins up thousands of machines and helps them 'talk' to each other and a second layer runs software. By 2018, OpenAI Five had played around 180 years worth of games in reinforcement learning running on 256 GPUs and 128,000 CPU cores, using Proximal Policy Optimization, a policy gradient method. == Comparisons with other game AI systems == Prior to OpenAI Five, other AI versus human experiments and systems have been successfully used before, such as Jeopardy! with Watson, chess with Deep Blue, and Go with AlphaGo. In comparison with other games that have used AI systems to play against human players, Dota 2 differs as explained below: Long run view: The bots run at 30 frames per second for an average match time of 45 minutes, which results in 80,000 ticks per game. OpenAI Five observes every fourth frame, generating 20,000 moves. By comparison, chess usually ends before 40 moves, while Go ends before 150 moves. Partially observed state of the game: Players and their allies can only see the map directly around them. The rest of it is covered in a fog of war which hides enemies units and their movements. Thus, playing Dota 2 requires making inferences based on this incomplete data, as well as predicting what their opponent could be doing at the same time. By comparison, Chess and Go are "full-information games", as they do not hide elements from the opposing player. Continuous action space: Each playable character in a Dota 2 game, known as a hero, can take dozens of actions that target either another unit or a position. The OpenAI Five developers allow the space into 170,000 possible actions per hero. Without counting the perpetual aspects of the game, there are an average of ~1,000 valid actions each tick. By comparison, the average number of actions in chess is 35 and 250 in Go. Continuous observation space: Dota 2 is played on a large map with ten heroes, five on each team, along with dozens of buildings and non-player character (NPC) units. The OpenAI system observes the state of a game through developers' bot API, as 20,000 numbers that constitute all information a human is allowed to get access to. A chess board is represented as about 70 lists, whereas a Go board has about 400 enumerations. == Reception == OpenAI Five have received acknowledgement from the AI, tech, and video game community at large. Microsoft founder Bill Gates called it a "big deal", as their victories "required teamwork and collaboration". Chess champion Garry Kasparov, who lost against the Deep Blue AI in 1997, stated that despite their losing performance at The International 2018, the bots would eventually "get there, and sooner than expected". In a conversation with MIT Technology Review, AI experts also considered OpenAI Five system as a significant achievement, as they noted that Dota 2 was an "extremely complicated game", so even beating non-professional players was impressive. PC Gamer wrote that their wins against professional players was a significant event in machine learning. In contrast, Motherboard wrote that the victory was "basically cheating" due to the simplified hero pools on both sides, as well as the fact that bots were given direct access to the API, as opposed to using computer vision to interpret pixels on the screen. The Verge wrote that the bots were evidence that the company's approach to reinforcement learning and its general philosophy about AI was "yielding milestones". In 2019, DeepMind unveiled a similar bot for StarCraft II, AlphaStar. Like OpenAI Five, AlphaStar used reinforcement learning and self-play. The Verge reported that "the goal with this type of AI research is not just to crush humans in various games just to prove it can be done. Instead, it's to prove that — with enough time, effort, and resources — sophisticated AI software can best humans at virtually any competitive cognitive challenge, be it a board game or a modern video game." They added that the DeepMind and OpenAI victories were also a testament to the power of certain uses of reinforcement learning. It was OpenAI's hope that the technology could have applications outside of the digital realm. In 2018, they were able to reuse the same reinforcement learning algorithms and training code from OpenAI Five for Dactyl, a human-like robot hand with a neural network built to manipulate physical objects. In 2019, Dactyl solved the Rubik's Cube.

    Read more →
  • General Problem Solver

    General Problem Solver

    General Problem Solver (GPS) is a computer program created in 1957 by Herbert A. Simon, J. C. Shaw, and Allen Newell (RAND Corporation) intended to work as a universal problem solver machine. In contrast to the former Logic Theorist project, the GPS works with means–ends analysis. == Overview == Any problem that can be expressed as a set of well-formed formulas (WFFs) or Horn clauses, and that constitutes a directed graph with one or more sources (that is, hypotheses) and sinks (that is, desired conclusions), can be solved, in principle, by GPS. Proofs in the predicate logic and Euclidean geometry problem spaces are prime examples of the domain of applicability of GPS. It was based on Simon and Newell's theoretical work on logic machines. GPS was the first computer program that separated its knowledge of problems (rules represented as input data) from its strategy of how to solve problems (a generic solver engine). GPS was implemented in the third-order programming language, IPL. While GPS solved simple problems such as the Towers of Hanoi that could be sufficiently formalized, it could not solve any real-world problems because the search was easily lost in the combinatorial explosion. Put another way, the number of "walks" through the inferential digraph became computationally untenable. (In practice, even a straightforward state space search such as the Towers of Hanoi can become computationally infeasible, albeit judicious prunings of the state space can be achieved by such elementary AI techniques as A and IDA). The user defined objects and operations that could be done on the objects, and GPS generated heuristics by means–ends analysis in order to solve problems. It focused on the available operations, finding what inputs were acceptable and what outputs were generated. It then created subgoals to get closer and closer to the goal. The GPS paradigm eventually evolved into the Soar architecture for artificial intelligence.

    Read more →