AI Video Generator Tools

AI Video Generator Tools — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

  • Concept drift

    Concept drift

    In predictive analytics, data science, machine learning and related fields, concept drift or drift is an evolution of data that invalidates the data model. It happens when the statistical properties of the target variable, which the model is trying to predict, change over time in unforeseen ways. This causes problems because the predictions become less accurate as time passes. Drift detection and drift adaptation are of paramount importance in the fields that involve dynamically changing data and data models. == Predictive model decay == In machine learning and predictive analytics this drift phenomenon is called concept drift. In machine learning, a common element of a data model are the statistical properties, such as probability distribution of the actual data. If they deviate from the statistical properties of the training data set, then the learned predictions may become invalid, if the drift is not addressed. == Data configuration decay == Another important area is software engineering, where three types of data drift affecting data fidelity may be recognized. Changes in the software environment ("infrastructure drift") may invalidate software infrastructure configuration. "Structural drift" happens when the data schema changes, which may invalidate databases. "Semantic drift" is changes in the meaning of data while the structure does not change. In many cases this may happen in complicated applications when many independent developers introduce changes without proper awareness of the effects of their changes in other areas of the software system. For many application systems, the nature of data on which they operate are subject to changes for various reasons, e.g., due to changes in business model, system updates, or switching the platform on which the system operates. In the case of cloud computing, infrastructure drift that may affect the applications running on cloud may be caused by the updates of cloud software. There are several types of detrimental effects of data drift on data fidelity. Data corrosion is passing the drifted data into the system undetected. Data loss happens when valid data are ignored due to non-conformance with the applied schema. Squandering is the phenomenon when new data fields are introduced upstream in the data processing pipeline, but somewhere downstream these data fields are absent. == Inconsistent data == "Data drift" may refer to the phenomenon when database records fail to match the real-world data due to the changes in the latter over time. This is a common problem with databases involving people, such as customers, employees, citizens, residents, etc. Human data drift may be caused by unrecorded changes in personal data, such as place of residence or name, as well as due to errors during data input. "Data drift" may also refer to inconsistency of data elements between several replicas of a database. The reasons can be difficult to identify. A simple drift detection is to run checksum regularly. However the remedy may be not so easy. == Examples == The behavior of the customers in an online shop may change over time. For example, if weekly merchandise sales are to be predicted, and a predictive model has been developed that works satisfactorily. The model may use inputs such as the amount of money spent on advertising, promotions being run, and other metrics that may affect sales. The model is likely to become less and less accurate over time – this is concept drift. In the merchandise sales application, one reason for concept drift may be seasonality, which means that shopping behavior changes seasonally. Perhaps there will be higher sales in the winter holiday season than during the summer, for example. Concept drift generally occurs when the covariates that comprise the data set begin to explain the variation of your target set less accurately — there may be some confounding variables that have emerged, and that one simply cannot account for, which renders the model accuracy to progressively decrease with time. Generally, it is advised to perform health checks as part of the post-production analysis and to re-train the model with new assumptions upon signs of concept drift. == Possible remedies == To prevent deterioration in prediction accuracy because of concept drift, reactive and tracking solutions can be adopted. Reactive solutions retrain the model in reaction to a triggering mechanism, such as a change-detection test or control charts from statistical process control, to explicitly detect concept drift as a change in the statistics of the data-generating process. When concept drift is detected, the current model is no longer up-to-date and must be replaced by a new one to restore prediction accuracy. A shortcoming of reactive approaches is that performance may decay until the change is detected. Tracking solutions seek to track the changes in the concept by continually updating the model. Methods for achieving this include online machine learning, frequent retraining on the most recently observed samples, and maintaining an ensemble of classifiers where one new classifier is trained on the most recent batch of examples and replaces the oldest classifier in the ensemble. Contextual information, when available, can be used to better explain the causes of the concept drift: for instance, in the sales prediction application, concept drift might be compensated by adding information about the season to the model. By providing information about the time of the year, the rate of deterioration of your model is likely to decrease, but concept drift is unlikely to be eliminated altogether. This is because actual shopping behavior does not follow any static, finite model. New factors may arise at any time that influence shopping behavior, the influence of the known factors or their interactions may change. Concept drift cannot be avoided for complex phenomena that are not governed by fixed laws of nature. All processes that arise from human activity, such as socioeconomic processes, and biological processes are likely to experience concept drift. Therefore, periodic retraining, also known as refreshing, of any model is necessary. === Remedy methods === DDM (Drift Detection Method): detects drift by monitoring the model's error rate over time. When the error rate passes a set threshold, it enters a warning phase, and if it passes another threshold, it enters a drift phase. EDDM (Early Drift Detection Method): improves DDM's detection rate by tracking the average distance between two errors instead of only the error rate. ADWIN (Adaptive Windowing): dynamically stores a window of recent data and warns the user if it detects a significant change between the statistics of the window's earlier data compared to more recent data. KSWIN (Kolmogorov–Smirnov Windowing): detects drift based on the Kolmogorov-Smirnov statistical test. DDM and EDDM: Concept Drift Detection online supervised methods that rely on sequential error monitoring to estimate the evolving error rate. ADWIN and KSWIN: Windowing maintain a "window", a subset of the most recent data, of the data stream, which it checks for statistical differences across the window. == Applications in security == Concept drift is a recurring issue in security analytics, especially in malware and intrusion detection. In these systems, models are often trained on past logs, binaries or network traces, but the behaviour of attackers changes over time as new malware families, obfuscation techniques and campaigns appear. When the data no longer resemble the training set, the decision boundaries learned by classifiers or anomaly detectors can become misaligned with the current threat landscape and detection performance can drop unless the models are updated or replaced. Several studies on Windows malware model detection as an evolving data stream and track how performance changes as time passes. They show that classifiers trained on a fixed time window can perform well on nearby data but deteriorate quickly when evaluated on samples collected months or years later, even when large amounts of training data are available. In order to keep up with this, security systems often use sliding or adaptive windows, which restrict training to the most recent portion of the data so that older, less relevant examples are gradually discarded. They also employ drift detectors such as ADWIN and KSWIN that monitor error rates or changes in the distribution of recent observations and signal when the statistics of the incoming stream differ significantly from the past, prompting retraining or model replacement. Related problems appear in spam filtering, fraud detection and intrusion detection, where adversaries change content, patterns of activity or network behavior to evade models trained on historical data. In these settings drift can be gradual, as new types of spam or fraud emerge, or abrupt, after a sudden shift in attack techniques. Common strategies to remain eff

    Read more →
  • Inbenta

    Inbenta

    Inbenta is an AI company that originated in Barcelona, Spain, in 2005. Inbenta is currently headquartered in Allen, Texas, with additional offices in Spain, São Paulo, Brazil, Toulouse, France, and Tokyo, Japan. Inbenta provides natural language processing and semantic search through artificial intelligence. == History == Inbenta raised $12 Million in their Series B funding round to extend the reach of their artificial intelligence for business solutions. In 2023 Inbenta's new chief executive officer Melissa Solis moved Inbenta's headquarters to One Bethany West in Allen, Texas from Foster City, California. == Controversy == On 23 June 2018, Ticketmaster UK identified malicious software on a customer support product hosted by Inbenta Technologies, compromising personal data and payment details for thousands of Ticketmaster customers. Three days later, Inbenta's CEO Issued a message about the incident to convey the full scope of the breach. Also on its FAQ section, Inbenta claimed that "After a careful analysis of all clues and snapshots from our systems, the technical team at Inbenta discovered that the script had been implemented on the payment page. We were unaware of this, and would have advised against doing so had we known, as it presents a point of vulnerability". On November 13, 2020, the Information Commissioner's Office fined Ticketmaster UK Limited £1.25 million for failing to protect customers' payment details. According to the ICO, "It was because of Ticketmaster's business decision to include the [Inbenta] chat bot on its payment page that the chat bot was able to unlawfully process the personal data of customers."

    Read more →
  • Suggested Upper Merged Ontology

    Suggested Upper Merged Ontology

    The Suggested Upper Merged Ontology (SUMO) is an upper ontology intended as a foundation ontology for a variety of computer information processing systems. SUMO defines a hierarchy of classes and related rules and relationships. These are expressed in a version of the language SUO-KIF, a higher-order logic that has a LISP-like syntax, as well as the TPTP family of languages. A mapping from WordNet synsets to SUMO has been defined. Initially, SUMO was focused on meta-level concepts (general entities that do not belong to a specific problem domain), and thereby would lead naturally to a categorization scheme for encyclopedias. It has now been considerably expanded to include a mid-level ontology and dozens of domain ontologies. SUMO is organized for interoperability of automated reasoning engines. To maximize compatibility, schema designers can try to assure that their naming conventions use the same meanings as SUMO for identical words (for example, "agent" or "process"). SUMO has an associated open source Sigma knowledge engineering environment. Initially, Sumo was developed by the Teknowledge Corporation and now is maintained by Articulate Software. SUMO is open source. The first release was in December 2000.

    Read more →
  • InRule Technology

    InRule Technology

    InRule Technology is a software company that offers Business Rule Management System (BRMS) enterprise software products. == History == InRule Technology's Chief Executive Officer Rik Chomko and Chief Technology Officer Loren Goodman founded InRule Technology in Chicago in 2002. Paul Hessinger joined InRule Technology in 2004 as chief executive officer and chairman of the board and served until his retirement in 2015. They work with companies in several markets, including financial services, public sector, healthcare, and insurance. In 2007, InRule Technology became a charter member of the Microsoft Business Process Alliance. In August 2019, InRule was acquired by Open Gate Capital. == Products == On October 29, 2012, InRule Technology launched InRule for Microsoft Dynamics CRM. The program provides components to enable creation and update of rules within Microsoft Dynamics CRM, InRule for Microsoft Dynamics CRM provides a platform for shops that prefer to work with Microsoft's platforms. With the availability of InRule 4.6 in 2014, the company introduced deployment of InRule through REST services and allowed REST services to be called from InRule. This enables access to data exposed as a REST service and to package up a rule service for RESTful access. The product launch reflected the move of the company's core audience to use a broader array of technologies despite an earlier focus on .NET. In 2017, InRule introduced InRule for the Salesforce Platform, as well as a technology partnership with Work-Relay, a Business Process Management (BPM) application built on the Salesforce Platform. One year earlier the company introduced InRule for JavaScript, allowing enterprises to run rules on the client-side, server-side or both. The software architecture includes multiple components, including irAuthor, the primary authoring tool for creating and maintaining rules; irVerify, a real-time test environment to run and debug rule applications; and irSDK, a set of APIs that allows developers to integrate inRule into their applications. Additionally, irSOA allows users to access the InRule rule engine as a service. irSOA is now called the irServer Execution Service.

    Read more →
  • Digital image

    Digital image

    A digital image is an image composed of picture elements, also known as pixels, each with finite, discrete quantities of numeric representation for its intensity or gray level that is an output from its two-dimensional functions fed as input by its spatial coordinates denoted with x, y on the x-axis and y-axis, respectively. An image can be vector or raster type. By itself, the term "digital image" usually refers to raster images or bitmapped images (as opposed to vector images). == Raster == Raster images have a finite set of digital values, called picture elements or pixels. The digital image contains a fixed number of rows and columns of pixels. Pixels are the smallest individual element in an image, holding quantized values that represent the brightness of a given color at any specific point. Typically, the pixels are stored in computer memory as a raster image or raster map, a two-dimensional array of small integers. These values are often transmitted or stored in a compressed form. Raster images can be created by a variety of input devices and techniques, such as digital cameras, scanners, coordinate-measuring machines, seismographic profiling, airborne radar, and more. They can also be synthesized from arbitrary non-image data, such as mathematical functions or three-dimensional geometric models; the latter being a major sub-area of computer graphics. The field of digital image processing is the study of algorithms for their transformation. === Raster file formats === Most users come into contact with raster images through digital cameras, which use any of several image file formats. Some digital cameras give access to almost all the data captured by the camera, using a raw image format. The Universal Photographic Imaging Guidelines (UPDIG) suggests these formats be used when possible since raw files produce the best quality images. These file formats allow the photographer and the processing agent the greatest level of control and accuracy for output. Their use is inhibited by the prevalence of proprietary information (trade secrets) for some camera makers, but there have been initiatives such as OpenRAW to influence manufacturers to release these records publicly. An alternative may be Digital Negative (DNG), a proprietary Adobe product described as "the public, archival format for digital camera raw data". Although this format is not yet universally accepted, support for the product is growing, and increasingly professional archivists and conservationists, working for respectable organizations, variously suggest or recommend DNG for archival purposes. == Vector == Vector images resulted from mathematical geometry (vector). In mathematical terms, a vector consists of both a magnitude, or length, and a direction. Often, both raster and vector elements will be combined in one image; for example, in the case of a billboard with text (vector) and photographs (raster). Example of vector file types are EPS, PDF, and AI. == Image viewing == Image viewer software displayed on images. Web browsers can display standard internet images formats including JPEG, GIF and PNG. Some can show SVG format which is a standard W3C format. In the past, when the Internet was still slow, it was common to provide "preview" images that would load and appear on the website before being replaced by the main image (to give a preliminary impression). Now Internet is fast enough and this preview image is seldom used. Some scientific images can be very large (for instance, the 46 gigapixel size image of the Milky Way, about 194 GB in size). Such images are difficult to download and are usually browsed online through more complex web interfaces. Some viewers offer a slideshow utility to display a sequence of images. == History == Early digital fax machines such as the Bartlane cable picture transmission system preceded digital cameras and computers by decades. The first picture to be scanned, stored, and recreated in digital pixels was displayed on the Standards Eastern Automatic Computer (SEAC) at NIST. The advancement of digital imagery continued in the early 1960s, alongside development of the space program and in medical research. Projects at the Jet Propulsion Laboratory, MIT, Bell Labs and the University of Maryland, among others, used digital images to advance satellite imagery, wirephoto standards conversion, medical imaging, videophone technology, character recognition, and photo enhancement. Rapid advances in digital imaging began with the introduction of MOS integrated circuits in the 1960s and microprocessors in the early 1970s, alongside progress in related computer memory storage, display technologies, and data compression algorithms. The invention of computerized axial tomography (CAT scanning), using x-rays to produce a digital image of a "slice" through a three-dimensional object, was of great importance to medical diagnostics. As well as origination of digital images, digitization of analog images allowed the enhancement and restoration of archaeological artifacts and began to be used in fields as diverse as nuclear medicine, astronomy, law enforcement, defence and industry. Advances in microprocessor technology paved the way for the development and marketing of charge-coupled devices (CCDs) for use in a wide range of image capture devices and gradually displaced the use of analog film and tape in photography and videography towards the end of the 20th century. The computing power necessary to process digital image capture also allowed computer-generated digital images to achieve a level of refinement close to photorealism. === Digital image sensors === The first semiconductor image sensor was the CCD, developed by Willard S. Boyle and George E. Smith at Bell Labs in 1969. While researching MOS technology, they realized that an electric charge was the analogy of the magnetic bubble and that it could be stored on a tiny MOS capacitor. As it was fairly straightforward to fabricate a series of MOS capacitors in a row, they connected a suitable voltage to them so that the charge could be stepped along from one to the next. The CCD is a semiconductor circuit that was later used in the first digital video cameras for television broadcasting. Early CCD sensors suffered from shutter lag. This was largely resolved with the invention of the pinned photodiode (PPD). It was invented by Nobukazu Teranishi, Hiromitsu Shiraki and Yasuo Ishihara at NEC in 1980. It was a photodetector structure with low lag, low noise, high quantum efficiency and low dark current. In 1987, the PPD began to be incorporated into most CCD devices, becoming a fixture in consumer electronic video cameras and then digital still cameras. Since then, the PPD has been used in nearly all CCD sensors and then CMOS sensors. The NMOS active-pixel sensor (APS) was invented by Olympus in Japan during the mid-1980s. This was enabled by advances in MOS semiconductor device fabrication, with MOSFET scaling reaching smaller micron and then sub-micron levels. The NMOS APS was fabricated by Tsutomu Nakamura's team at Olympus in 1985. The CMOS active-pixel sensor (CMOS sensor) was later developed by Eric Fossum's team at the NASA Jet Propulsion Laboratory in 1993. By 2007, sales of CMOS sensors had surpassed CCD sensors. === Digital image compression === An important development in digital image compression technology was the discrete cosine transform (DCT), a lossy compression technique first proposed by Nasir Ahmed in 1972. DCT compression is used in JPEG, which was introduced by the Joint Photographic Experts Group in 1992. JPEG compresses images down to much smaller file sizes, and has become the most widely used image file format on the Internet. == Mosaic == In digital imaging, a mosaic is a combination of non-overlapping images, arranged in some tessellation. Gigapixel images are an example of such digital image mosaics. Satellite imagery are often mosaicked to cover Earth regions. Interactive viewing is provided by virtual-reality photography.

    Read more →
  • Composite portrait

    Composite portrait

    Composite portraiture (also known as composite photographs) is a technique invented by Sir Francis Galton in the 1880s after a suggestion by Herbert Spencer for registering photographs of human faces on the two eyes to create an "average" photograph of all those in the photographed group. Spencer had suggested using onion paper and line drawings, but Galton devised a technique for multiple exposures on the same photographic plate. He noticed that these composite portraits were more attractive than any individual member, and this has generated a large body of research on human attractiveness and averageness one hundred years later. He also suggested in a Royal Society presentation in 1883 that the composites provided an interesting concrete representation of human ideal types and concepts. He discussed using the technique to investigate characteristics of common types of humanity, such as criminals. In his mind, it was an extension of the statistical techniques of averages and correlation. In this sense, it represents one of the first implementations of convolution factor analysis and neural networks in the understanding of knowledge representation in the human mind. Galton also suggested that the technique could be used for creating natural types of common objects. During the late 19th century, English psychometrician Sir Francis Galton attempted to define physiognomic characteristics of health, disease, beauty, and criminality, via a method of composite photography. Galton's process involved the photographic superimposition of two or more faces by multiple exposures. After averaging together photographs of violent criminals, he found that the composite appeared "more respectable" than any of the faces comprising it; this was likely due to the irregularities of the skin across the constituent images being averaged out in the final blend. Since the advancement of computer graphics technology in the early 1990s, Galton's composite technique has been adopted and greatly improved using computer graphics software.

    Read more →
  • Ian Goodfellow

    Ian Goodfellow

    Ian J. Goodfellow (born 1987) is an American computer scientist, engineer, and executive, most noted for his work on artificial neural networks and deep learning. He is a research scientist at Google DeepMind, was previously employed as a research scientist at Google Brain and director of machine learning at Apple as well as one of the first employees at OpenAI, and has made several important contributions to the field of deep learning, including the invention of the generative adversarial network (GAN). Goodfellow co-wrote, as the first author, the textbook Deep Learning (2016) and wrote the chapter on deep learning in the authoritative textbook of the field of artificial intelligence, Artificial Intelligence: A Modern Approach (used in more than 1,500 universities in 135 countries). == Education == Goodfellow obtained his BSc and MSc in computer science from Stanford University under the supervision of Andrew Ng, and his PhD in machine learning from the Université de Montréal in February 2015, under the supervision of Yoshua Bengio and Aaron Courville. Goodfellow's thesis is titled Deep learning of representations and its application to computer vision. == Career == After graduation, Goodfellow joined Google as part of the Google Brain research team. In March 2016, he left Google to join the newly founded OpenAI research laboratory. 11 months later, in March 2017, Goodfellow returned to Google Research, but left again in 2019. In 2019, Goodfellow joined Apple as director of machine learning in the Special Projects Group. He resigned from Apple in April 2022 to protest Apple's plan to require in-person work for its employees. Shortly after, Goodfellow then joined Google DeepMind as a research scientist. In 2025, Goodfellow left Google. As of July 2026, based on information on Goodfellow's LinkedIn profile, he is co-founding a startup company. == Research == Goodfellow is best known for inventing generative adversarial networks (GANs), using deep learning to generate images. This approach uses two neural networks to competitively improve an image's quality. A “generator” network creates a synthetic image based on an initial set of images such as a collection of faces. A “discriminator” network tries to determine whether images are authentic or created by the generator. The generate-detect cycle is repeated. For each iteration, the generator and the discriminator use the other's feedback to improve or detect the generated images, until the discriminator can no longer distinguish between generated and authentic images. However, GANs have also been used to create deepfakes. At Google, Goodfellow developed a system enabling Google Maps to automatically transcribe addresses from photos taken by Street View cars and demonstrated security vulnerabilities of machine learning systems. == Recognition == In 2017, Goodfellow was cited in MIT Technology Review's 35 Innovators Under 35. In 2019, he was included in Foreign Policy's list of 100 Global Thinkers.

    Read more →
  • Jarosław Królewski

    Jarosław Królewski

    Jarosław Królewski ([jaˈrɔswaf kruˈlɛfskʲi]; born September 26, 1986) is a Polish entrepreneur, programmer, sociologist, investor, and philanthropist from Hańczowa, Poland. He is a researcher and lecturer at the AGH University of Krakow. He was selected as a Young Global Leader by the World Economic Forum in 2025. Królewski is a cofounder and chief executive of the software development company Synerise that develops its namesake business intelligence software based on artificial intelligence and big data. He is also the president and a majority stakeholder of the Polish soccer club Wisła Kraków. == Biography == === Scientific activities === Królewski graduated from the AGH University of Kraków and the University of Banking and Management in Kraków. He completed two fields of study: a master's degree in sociology, and an engineer's degree in computer science. He co-created innovative study programs, including social informatics and electronic business, recognized as the most innovative field of study in Poland in 2012 by the Ministry of Science and Higher Education, which led to the AGH receiving a PLN 1 million award for the development of the program. Królewski is a research and teaching employee at AGH, where since 2010 he has been conducting classes and lectures on the Internet, mobile technologies, and UX/UI. He has been preparing a PhD thesis. He is the brand ambassador of the Academy. He is also a mentor of the Polish Development Fund network. In 2019, on the occasion of the AGH University's 100th anniversary, Królewski was honored the title of "AGH Graduate Junior 2018." Królewski is the co-originator of the "Data Science in Business and Administration" doctoral studies organized by the Faculty of Computer Science and Electronic Economy of the Poznań University of Economics. He is a co-author of a textbook E-marketing. Contemporary trends. Starter package (2013), and an Book on algorithmic governance Algocracy. How and why artificial intelligence changes everything (with Krzysztof Rybiński, 2023). === Business career === Throughout the 2000s, Królewski was responsible for issues of usability and user experience at the advertising agency Eskadra in Kraków. In 2012, along with programmer Miłosz Baluś and graphic designer Krzysztof Kochmański, he founded the software house Humanoit Group. The company created a project management software using machine learning and artificial intelligence. In 2013, HG Intelligence was established to create a platform for analytics and automation of business processes called "Synerise" that combined big data with artificial intelligence mechanisms. Królewski became the president of the company's management board. In 2016, the company rebranded itself after its own platform. It is one of the fastest growing enterprises in Poland – in 2019 it was valued at USD 85 million (PLN 323.5 million), and its value is still growing, in 2022 it announced an investment of USD 23 million. Królewski is a supporter of releasing some software in open-source form, an example of which is the open library Cleora.ai. Królewski has been described "one of the most promising young Polish businessmen in the technology industry." According to Forbes, he is a "visionary computer scientist who in many respects resembles the young Bill Gates." Królewski considers himself a “technological determinist and optimist.” He never wants to be a millionaire or billionaire, he spends 80 percent of his private income on education, sports and charities. === Sports === In his youth (2002–2006) he was a football player of the (then 4th-league) club Glinik Gorlice, and represented it at the then-highest level of junior competitions in Poland. He played there with Rafał Wisłocki, later president of Wisła Kraków and vice-president of Bruk-Bet Termalica Nieciecza. In early 2019, Królewski was the initiator of a rescue operation that saved Wisła Kraków from bankruptcy, as well as the originator of the crowdfunding issue of shares of Wisła Kraków, pioneering in Polish sports, during restructuring and searching for a strategic investor. The offered shares constituted 5.1 percent. all the company's shares, which meant that the club was valued at PLN 74.4 million. 40,000 shares were put up for sale, each worth PLN 100. Within 24 hours, they were purchased by 9,124 investors through an equity crowdfunding platform Beesfund, earning the club PLN 4 million. In March 2019, Królewski became vice-chairman of Wisła's supervisory board, a position he held until 2021. In April 2020, he became Wisła's co-owner, along with the footballer Jakub Błaszczykowski, and Tomasz Jażdżyński, president of Gremi Media (publisher of the news outlets Rzeczpospolita and Parkiet). The three granted a bridging loan to the club of PLN 4 million, each supporting PLN 1.33 million. The funds were used to repay the club's debts to players. In November 2022, the supervisory board of Wisła Kraków appointed Królewski as the president of the club's management board. In December 2022, Królewski took over a majority stake in the club. In January 2024, based on match statistics, he used AI tools to select Wisła's new coach, Albert Rudé. === Social activities === Królewski is the creator and originator of the nationwide educational project "AI Schools & Academy", the first artificial intelligence teaching program in Polish kindergartens, primary and secondary schools in Polish history. Launched in 2018, the project was financed by Synerise business partners: Carrefour, CCC, Ernst & Young, IDC, Media Expert, Microsoft, Orange Foundation, Oriflame, Bank Pekao, Photon, PZU, and Żabka. Physicists, mathematicians, and computer scientists conduct special classes in 1,500 kindergartens, primary and secondary schools. Outstanding students and teachers are awarded scholarships. The project was appreciated by experts. In the years 2018–2020, Królewski was the main sponsor of Glinik Gorlice. He also supported the women's football team Staszkówka Jelna (of Staszkówka). After taking over the shares of Wisła Kraków in 2020, he launched socially conscience initiatives along with other shareholders, including a women's football team, the amp football section, and the blind football section. He has privately sponsored social charities. == Accolades and awards == In 2017, Królewski along with the Synerise co-founders Baluś and Kochmański was included in the “New Europe 100” list of eastern Europe's brightest and best citizens changing the region's societies, politics, or business environments, according to Res Publica, along with the International Visegrad Fund, Google and the Financial Times. Królewski was included on Ernst & Young's list of the 30 most promising technology entrepreneurs in the world. In 2018, he was honored with the Special Jury Award in the Polish edition of the Ernst & Young Entrepreneur of the Year Award competition, for combining scientific activities with entrepreneurship. The same year, Królewski won an award in the competition Digital Shapers, distinguishing outstanding tech personalities by the Digital Poland Foundation. He was also selected to Ernst & Young startup program EY Accelerating Entrepreneurs for businesses that focus on disruptive fields. In 2019, as part of the AI Awards competition, Królewski received the title of AI Person of the Year. == Private life == Królewski comes from a Lemko family from Hańczowa in the Low Beskids. He is married to Aleksandra Królewska.

    Read more →
  • Online OS

    Online OS

    The Online Operating System was a fully multi-lingual and free to use web desktop written in JavaScript using Ajax. It was a Windows-based desktop environment with open-source applications and system utilities developed upon the reBOX web application framework by iCUBE Network Solutions, an Austrian company located in Vienna. == About the project == OOS.cc, which is short for Online Operating System, was a web application platform that mimicked the look and feel of classic desktop operating systems such as Microsoft Windows, Mac OS X or KDE. It consisted of various open source applications built upon the so-called reBOX web application framework. As applications could be executed in an integrated and parallel way, the OOS could have been considered a web desktop or webtop. It provided basic services such as a GUI, a virtual file system, access control management and possibilities to develop and deploy applications online. As the Online Operating System was executed within a web browser, it was no real operating system but rather a portal to various web applications, offering a high usability and flexibility. The project was partly funded by grants from the Internetprivatstiftung Austria (IPA). As at 01.08.2008 almost 20.000 users have joined the oos.cc community, using the offered featured and applications. == History == The development of the web desktop was started by iCUBE Network Solutions in 2005, followed by the first beta releases in 2006. Hence, together with YouOS and eyeOS, it can be considered to be one of the first publicly available systems of its kind. The first full version including core-level multi-language support, the file system and a basic set of applications was released to the public in March 2007 on the occasion of a national exhibition (ITnT Austria Archived 2007-06-30 at the Wayback Machine) and has left beta state half a year later in October 2007. The first release considered stable (1.0.0) was published in July 2007. The project itself and the contained applications have received several national innovation awards (see,) and have gained attention mainly due to the comprehensive approach taken (see,). OOS.cc started as a national project. The full platform including all offered applications are currently available in three languages (German, English as well as Spanish) and is receiving increasing coverage around the world (for examples see, or). The current version is 1.3.01 from 01.08.2008. == Technical overview == The project is fully written in JavaScript, exclusively using DHTML techniques to run in any web browser without any additional software installation needed. The system implements a modern kind of web application model, excessively using Ajax for communicating between client components and the Java server backend in an exclusively asynchronous manner. Aim is to offer users the unique interaction behavior following the desktop metaphor, which is the main idea of any web desktop. Also typical for this sort of web application is the broadly use of Javascript-on-demand techniques, cutting the complete project source into pieces and loading them instantly when needed. Based on this technical basis, reBOX was the framework library all applications in oos.cc were built of. It is a fully flexible and extensible API, including a GUI widget set, communication mechanisms and server services offering general and framework specific services. The Online Operating System itself consisted of a basic framework, which was able to launch any JavaScript application using the reBOX library. The user interface was based on the behavior of the Windows desktop with a start menu, a task bar and a desktop background. All applications were running in this environment. At server side, there were Java based web services that ran to serve the client processes and to provide data from the relational database in the backend. oos.cc also provided an integrated development environment called Developer Suite, which allowed the community to build own applications for the desktop environment based on reBOX (see development section below). == License == All applications available in oos.cc were open source under the European Union Public Licence (EUPL). The reBOX development toolkit is free to use developing any applications for the webtop. == Features == As mentioned above, all applications published on oos.cc are open source based on the EUPL, and can be "installed" or "deinstalled" to what-ever preferences the user has. Besides global services like the multi-language support or the global theme support, as well as some minor tools and games, oos.cc offered four major services that could be used completely free of charge. Integrated and fully flexible file storage (1 GB per user) HTTP as well as FTP file transfer from and to local file system User-based file-shares within the oos-community WebDAV access Document Management (including Version Control and File Locking mechanisms) Image publishing, organization and post-processing A free sub domain (user.oos.cc) for web- or image publishing, directly integrated in the desktop Groupware applications, including free mail, fetchmail and contact management An integrated development environment where oos-applications can be created directly from within the system (see development section below) Next releases were planned to focus on an extensive security and privacy suite, dealing with challenges like anonymous communication (browsing as well as temporary mail-addresses) as well as offering encrypted password and file storage and connectivity services. Since its initial stable release, OOS.cc could have been accessed using https to ensure secure communication. == Limitations and drawbacks == Limited number of applications: no commercial applications can be hosted. Only reviewed applications are being published No processing of popular office formats (.doc, .odt, etc.) Limited language support: Only English, German and Spanish Dependence on foreign infrastructure: No possibility to extend storage, no additional/guaranteed bandwidth, etc. == Development == One of the key focuses of the team was right from the beginning to offer a very flexible and comprehensive API, that can be used to develop not only custom applications within oos.cc, but also stand-alone web-applications or to integrate single components in existing web-sites. By decoupling the development from web-related "problems" using the reBOX API web-applications can be development in a similar fashion to any Java program: Elements can be positioned and can interact like in high-level object oriented programming languages, without taking care of divs, browser specific behavior or communication handling. The framework also offers multi-language and theme support for existing as well as newly created applications, allowing changing almost every aspect of the look and feel of the used components according to the preferences of its users. For taking advantage of this approach, one of the applications offered in the OOS was an integrated Development Suite, allowing directly writing and executing code and hence creating new programs within the boundaries of the web computer. All applications on oos.cc were released as open source, thus all existing programs were offered to be imported, reviewed or changed and then locally deployed. Following this idea, every user was free to submit changed or newly created applications to be included in the globally offered application set. The last release offered features like auto-completion and an outline-window.

    Read more →
  • SHRDLU

    SHRDLU

    SHRDLU is an early natural-language understanding computer program that was developed by Terry Winograd at MIT in 1968–1970. In the program, the user carries on a conversation with the computer, moving objects, naming collections and querying the state of a simplified "blocks world", essentially a virtual box filled with different blocks. SHRDLU was written in the Micro Planner and Lisp programming language on the DEC PDP-6 computer and a DEC graphics terminal. Later additions were made at the computer graphics labs at the University of Utah, adding a full 3D rendering of SHRDLU's "world". The name SHRDLU was derived from ETAOIN SHRDLU, the arrangement of the letter keys on a Linotype machine, arranged in descending order of usage frequency in English. == Functionality == SHRDLU is primarily a language parser that allows user interaction using English terms. The user instructs SHRDLU to move various objects around in the "blocks world" containing various basic objects such as blocks, cones and balls. SHRDLU combined four simple ideas to make the simulation of "understanding" more convincing. One was that SHRDLU's world is so simple that the entire set of objects and locations could be described by including as few as 50 words: nouns like "block" and "cone", verbs like "place on" and "move to", and adjectives like "big" and "blue". The possible combinations of these basic language building blocks are quite simple. SHRDLU also includes a basic memory to supply context. One could ask SHRDLU to "put the green cone on the red block" and then "take the cone off"; "the cone" would be taken to mean the green cone one had just talked about. SHRDLU can search back further through the interactions to find the proper context in most cases when additional adjectives were supplied. One could also ask questions about the history; for instance, one could ask "did you pick up anything before the cone?" A side effect of this memory, and the original rules SHRDLU was supplied with, is that the program can answer questions about what was possible in the world and what was not. For instance, SHRDLU can deduce that blocks could be stacked by looking for examples, but also realize that triangles could not be stacked, after having tried it. The "world" contains basic physics to make blocks fall over, independent of the language parser. Finally, SHRDLU can also remember names given to objects, or arrangements of them. For instance one could say "a steeple is a small triangle on top of a tall rectangle"; SHRDLU can then answer questions about steeples in the blocks world, and build new ones. This is an example of a SHRDLU session: Person: Pick up a big red block. Computer: OK. Person: Grasp the pyramid. Computer: I DON'T UNDERSTAND WHICH PYRAMID YOU MEAN. Person (changing their mind): Find a block which is taller than the one you are holding and put it into the box. Computer: BY "IT", I ASSUME YOU MEAN THE BLOCK WHICH IS TALLER THAN THE ONE I AM HOLDING. Computer: OK. Person: What does the box contain? Computer: THE BLUE PYRAMID AND THE BLUE BLOCK. Person: What is the pyramid supported by? Computer: THE BOX. Person: How many blocks are not in the box? Computer: FOUR OF THEM. Person: Is at least one of them narrower than the one which i told you to pick up? Computer: YES, THE RED CUBE. Person: Is it supported? Computer: YES, BY THE TABLE. Person: Can the table pick up blocks? Computer: NO. Person: Can a pyramid be supported by a block? Computer: YES. Person: Can a pyramid support a pyramid? Computer: I DON'T KNOW. Person: Stack up two pyramids. Computer: I CAN'T. Person: Will you please stack up both of the red blocks and either a green cube or a pyramid? Computer: OK. Person: Which cube is sitting on the table? Computer: THE LARGE GREEN ONE WHICH SUPPORTS THE RED PYRAMID. Person: Is there a large block behind a pyramid? Computer: YES, THREE OF THEM: A LARGE RED ONE, A LARGE GREEN CUBE, AND THE BLUE ONE. Person: Put a small one onto the green cube which supports a pyramid. Computer: OK. Person: Put the littlest pyramid on top of it. Computer: OK. Person: Does the shortest thing the tallest pyramid's support supports support anything green? Computer: YES, THE GREEN PYRAMID. Person: What color is it? Computer: BY "IT", I ASSUME YOU MEAN THE SHORTEST THING THE TALLEST PYRAMID'S SUPPORT SUPPORTS. Computer: RED Person: How many things are on top of green cubes? Computer: I'M NOT SURE WHAT YOU MEAN BY "ON TOP OF" IN THE PHRASE "ON TOP OF GREEN CUBES" . DO YOU MEAN: 1 - DIRECTLY ON THE SURFACE 2 - ANWHERE ON TOP OF ? Person: 2 Computer: THREE OF THEM. Person: Had you touched any pyramid before you put the green one on the little cube? Computer: YES, THE GREEN ONE. Person: When did you pick it up? Computer: WHILE I WAS STACKING UP THE RED CUBE, A LARGE RED BLOCK AND A LARGE GREEN CUBE. Person: Why? Computer: TO GET RID OF IT. Person: Why did you do that? Computer: TO CLEAN OFF THE RED CUBE. Person: Why did you clear off that cube? Computer: TO PUT IT ON A LARGE GREEN CUBE. Person: Why did you do that? Computer: TO STACK UP THE RED CUBE , A LARGE RED BLOCK AND A LARGE GREEN CUBE. Person: Why did you do that? Computer: BECAUSE YOU ASKED ME TO. Person: How did you do it? Computer: BY PUTTING A LARGE RED BLOCK ON THE TABLE ; THEN LETTING GO OF IT ; THEN PUTTING A LARGE GREEN CUBE ON IT ; THEN LETTING GO OF THAT CUBE ; THEN PUTTING THE RED CUBE ON THAT CUBE; THEN LETTING GO OF THAT CUBE. Person: How many objects did you touch while you were doing it? Computer: FOUR OF THEM. Person: What did the red cube support before you started to clean it off? Computer: THE GREEN PYRAMID. Person: There were five blocks to the left of the box then. Computer: NO, ONLY FOUR OF THEM: THE RED CUBE, TWO LARGE GREEN CUBES AND A LARGE RED BLOCK. Person: Put the blue pyramid on the block in the box. Computer: OK. Person: Is there anything which is bigger than every pyramid but is not as wide as the thing that supports it? Computer: YES, THE BLUE BLOCK. Person: Does a steeple Computer (interrupting): SORRY, I DON'T KNOW THE WORD "STEEPLE". Person: A "steeple" is a stack which contains two green cubes and a pyramid. Computer: I UNDERSTAND. Person: Are there any steeples now? Computer: NO. Person: Build one. Computer: OK. Person: Call the biggest block "superblock". Computer: OK. Person: Have you picked superblock up since we began? Computer: YES. Person: Why did you drop it? Computer: BY "IT", I ASSUME YOU MEAN THE SUPERBLOCK. I CAN'T EXPLAIN A NON-EXISTENT EVENT. Person: Is there anything to the right of the red pyramid? Computer: YES, FOUR THINGS: THE BOX, THE RED CUBE, THE BLUE PYRAMID AND THE BLOCK NAMED SUPERBLOCK Person: Thank you. Computer: YOU'RE WELCOME! == Consequences == SHRDLU was considered a tremendously successful demonstration of artificial intelligence (AI). This led other AI researchers to excessive optimism which was soon lost when later systems attempted to deal with situations with a more realistic level of ambiguity and complexity. Subsequent efforts of the SHRDLU type, such as Cyc, have tended to focus on providing the program with considerably more information from which it can draw conclusions. In a 1991 interview, Winograd said about SHRDLU: [...] the famous dialogue with SHRDLU where you could pick up a block, and so on, I very carefully worked through, line by line. If you sat down in front of it, and asked it a question that wasn't in the dialogue, there was some probability it would answer it. I mean, if it was reasonably close to one of the questions that was there in form and in content, it would probably get it. But there was no attempt to get it to the point where you could actually hand it to somebody and they could use it to move blocks around. And there was no pressure for that whatsoever. Pressure was for something you could demo. Take a recent example, Negroponte's Media Lab, where instead of "perish or publish" it's "demo or die." I think that's a problem. I think AI suffered from that a lot, because it led to "Potemkin villages", things which - for the things they actually did in the demo looked good, but when you looked behind that there wasn't enough structure to make it really work more generally. Though not intentionally developed as such, SHRDLU is considered the first known formal example of interactive fiction, as the user interacts with simple commands to move objects around a virtual environment, though lacking the distinct story-telling normally present in the interactive fiction genre. The 1976-1977 game Colossal Cave Adventure is broadly considered to be the first true work of interactive fiction.

    Read more →
  • Decision Model and Notation

    Decision Model and Notation

    In business analysis, the Decision Model and Notation (DMN) is a standard published by the Object Management Group. It is a standard approach for describing and modeling repeatable decisions within organizations to ensure that decision models are interchangeable across organizations. The DMN standard provides the industry with a modeling notation for decisions that will support decision management and business rules. The notation is designed to be readable by business and IT users alike. This enables various groups to effectively collaborate in defining a decision model: the business people who manage and monitor the decisions, the business analysts or functional analysts who document the initial decision requirements and specify the detailed decision models and decision logic, the technical developers responsible for the automation of systems that make the decisions. The primary goal of DMN is to offer a common notation that all business users can easily understand. This includes business analysts who develop decision requirements and models, technical developers who automate decisions, and businesspeople who manage and monitor those decisions. DMN serves as a standardized link between business decision design and implementation.[4] The DMN standard can be effectively used standalone but it is also complementary to the BPMN and CMMN standards. BPMN defines a special kind of activity, the Business Rule Task, which "provides a mechanism for the process to provide input to a business rule engine and to get the output of calculations that the business rule engine might provide" that can be used to show where in a BPMN process a decision defined using DMN should be used. DMN has been made a standard for Business Analysis according to BABOK v3. == Elements of the standard == The standard includes three main elements Decision Requirements Diagrams that show how the elements of decision-making are linked into a dependency network. Decision tables to represent how each decision in such a network can be made. Business context for decisions such as the roles of organizations or the impact on performance metrics. A Friendly Enough Expression Language (FEEL) that can be used to evaluate expressions in a decision table and other logic formats. == Use cases == The standard identifies three main use cases for DMN Defining manual decision making Specifying the requirements for automated decision-making Representing a complete, executable model of decision-making == Benefits == Using the DMN standard will improve business analysis and business process management, since other popular requirement management techniques such as BPMN and UML do not handle decision making growth of projects using business rule management systems or BRMS, which allow faster changes it facilitates better communications between business, IT and analytic roles in a company it provides an effective requirements modeling approach for predictive analytics projects and fulfills the need for "business understanding" in methodologies for advanced analytics such as CRISP-DM it provides a standard notation for decision tables, the most common style of business rules in a business rule management system (BRMS) == Relationship to BPMN == DMN has been designed to work with BPMN. Business process models can be simplified by moving process logic into decision services. DMN is a separate domain within the OMG that provides an explicit way to connect to processes in BPMN. Decisions in DMN can be explicitly linked to processes and tasks that use the decisions. This integration of DMN and BPMN has been studied extensively. DMN expects that the logic of a decision will be deployed as a stateless, side-effect free Decision Service. Such a service can be invoked from a business process and the data in the process can be mapped to the inputs and outputs of the decision service. == DMN BPMN example == As mentioned, BPMN is a related OMG Standard for process modeling. DMN complements BPMN, providing a separation of concerns between the decision and the process. The example here describes a BPMN process and DMN DRD (Decision Requirements Diagram) for onboarding a bank customer. Several decisions are modeled and these decisions will direct the processes response. === New bank account process === In the BPMN process model shown in the figure, a customer makes a request to open a new bank account. The account application provides the account representative with all the information needed to create an account and provide the requested services. This includes the name, address and various forms of identification. In the next steps of the work flow, the know your customer (KYC) services are called. In the KYC services, the name and address are validated; followed by a check against the international criminal database (Interpol) and the database of persons that are 'politically exposed persons (PEP)'. The PEP is a person who is either entrusted with a prominent political position or a close relative thereof. Deposits from persons on the PEP list are potentially corrupt. This is shown as two services on the process model. Anti-money-laundering (AML) regulations require these checks before the customer account is certified. The results of these services plus the forms of identification are sent to the Certify New Account decision. This is shown as a 'rule' activity, verify account, on the process diagram. If the new customer passes certification, then the account is classified into onboarding for business retail, retail, wealth management and high-value business. Otherwise the customer application is declined. The Classify New Customer Decision classifies the customer. If the verify-account process returns a result of 'Manual' then the PEP or the Interpol check returned a close match. The account representative must visually inspect the name and the application to determine if the match is valid and accept or decline the application. === Certify new account decision === An account is certified for opening if the individual's' address is verified, and if valid identification is provided, and if the applicant is not on a list of criminals or politically exposed persons. These are shown as sub-decisions below the 'certify new account' decision. The account verification services provides a 100% match of the applicants address. For identification to be valid, the customer must provide a driver's license, passport or government issued ID. The checks against PEP and Interpol are 'fuzzy' matches and return matching score values. Scores above 85 are considered a 'match' and scores between 65 and 85 would require a 'manual' screening process. People who match either of these lists are rejected by the account application process. If there is a partial match with a score between 65 and 85, against the Interpol or PEP list then the certification is set to manual and an account representative performs a manual verification of the applicant's data. These rules are reflected in the figure below, which presents the decision table for whether to pass the provided name for the lists checks. === Client category === The client's on-boarding process is driven by what category they fall in. The category is decided by the: Type of client, business or private The size of the funds on deposit And the estimated net worth This decision is shown below: There are 6 business rules that determine the client's category and these are shown in the decision table here: === Summary example === In this example, the outcome of the 'Verify Account' decision directed the responses of the new account process. The same is true for the 'Classify Customer' decision. By adding or changing the business rules in the tables, one can easily change the criteria for these decisions and control the process differently. Modeling is a critical aspect of improving an existing process or business challenge. Modeling is generally done by a team of business analysts, IT personnel, and modeling experts. The expressive modeling capabilities of BPMN allows business analyst to understand the functions of the activities of the process. Now with the addition of DMN, business analysts can construct an understandable model of complex decisions. Combining BPMN and DMN yields a very powerful combination of models that work synergistically to simplify processes. == Relationship to decision mining and process mining == Automated discovery techniques that infer decision models from process execution data have been proposed as well. Here, a DMN decision model is derived from a data-enriched event log, along with the process that uses the decisions. In doing so, decision mining complements process mining with traditional data mining approaches. == cDMN extension == Constraint Decision Model and Notation (cDMN) is a formal notation for expressing knowledge in a tabular, intuitive format. It extends DMN with constraint reasoning and related concepts while aiming to retain the us

    Read more →
  • National Security Commission on Artificial Intelligence

    National Security Commission on Artificial Intelligence

    The National Security Commission on Artificial Intelligence (NSCAI) was an independent commission of the United States of America from 2018 to 2021. Its mission was to make recommendations to the President and Congress to "advance the development of artificial intelligence, machine learning, and associated technologies to comprehensively address the national security and defense needs of the United States". The commission's 15 members were nominated by the United States Congress. The NSCAI was dissolved on 1 October 2021. == History and reporting == The NSCAI began working in March 2019 and by November 2019 it had received more than 200 classified and unclassified briefings to help with the creation of its final report due in 2021.On 4 November 2019, the NSCAI shared its interim report with Congress, where it explained the 27 initial judgements to base its ongoing work. In the interim report the commission also agreed on seven principles: Global leadership in AI technology is a national security priority AI adoption is an urgent imperative for national security A shared sense of responsibility for the American peoples security must be created from government officials and private sector leaders. It needs to find local AI talent and use it to attract the world’s best minds Actions used for the protection of America’s AI leadership against foreign threats needs to follow the principles of free enterprise, free inquiry and free flow of ideas. The technical limitations of AI are universally known, however, a strong desire remains for powerful, dependable, and secure AI systems. United States used AI must follow American values including the rule of law Fundamental areas of effort for the preservation of U.S. advantages were also agreed upon in the interim report of 2019. The NSCAI released its first report of recommendations in March 2020, most of which were included in the 2021 National Defense Authorization Act. In July 2020, the commission published the second report to Congress. It identified 35 actions for both Executive and Legislative branches, which were focused on six fundamental areas. This report was available to the public. In January 2021, a draft of the final report was presented at a panel led by Schmidt. The report recommended the US to use AI technology for military use and development. It issued its final report in March 2021, saying that the U.S. is not sufficiently prepared to defend or compete against China in the AI era. It was broken up into two parts, the first titled “Defending America in the AI Era”, and the second “Winning the Technology Competition”. The report spoke about China’s efforts and investments into integration and that it could very well take the lead in AI in the next few years. Additional suggestions were made to concentrate on AI in everything we do and to implement it into US national security on multiple levels, as well as focus on bringing in new talent to develop AI and to introduce it to the working force on both civilian and military levels. Another recommendation of the NSCAI report was to develop and provide China and Russia with alternative models that are based on norms and democratic values. The final report also included a proposed $40 billion budget for government spending. On 14 April 2021, NSCAI executive director Ylli Bajraktari and director of Research and Analysis Justin Lynch participated in an event held by the Center for Security and Emerging Technology (CSET) to discuss the final report findings. In October 2021, NSCAI chair Eric Schmidt founded the bipartisan, non-profit Special Competitive Studies Project (SCSP) through his family led non-profit Eric & Wendy Schmidt Fund for Strategic Innovation in order to carry on the NSCAI’s efforts and expand beyond national security. The Foundation for Defense of Democracies held an event in June 2023, called “Thinking Forward After the NSCAI and CSC: A Discussion on AI and Cyber Policy”, with former members of NSCAI on the moderation panel, including Eric Schmidt and Ylli Bajraktari. == Members == Members of the National Security Commission on Artificial Intelligence: Eric Schmidt (chair), former CEO of Google Robert Work (Vice Chair), former Deputy Secretary of Defense Mignon Clyburn, former Commissioner of the Federal Communications Commission Chris Darby, CEO of In-Q-Tel Kenneth M. Ford, CEO of the Florida Institute for Human and Machine Cognition Jose-Marie Griffiths, President of Dakota State University Eric Horvitz, Technical Fellow at Microsoft Katrina G. McFarland, former Assistant Secretary of Defense for Acquisition Jason Matheny, Director of the Center for Security and Emerging Technology at Georgetown University Gilman Louie, partner at Alsop Louie Partners William Mark, vice president at SRI International Andy Jassy, CEO of Amazon Web Services (AWS) Safra Catz, CEO of Oracle Steve Chien, Technical Fellow at Jet Propulsion Laboratory (JPL) Andrew Moore, Google/Alphabet == Recommendations == The report's recommendations include: Dramatically increasing non-defense federal spending on AI research and development, doubling every year from $2 billion in 2022, to $32 billion in 2026. That would bring it up to a level similar to spending on biomedical research A dramatic increase in undergraduate scholarship and graduate studies fellowships in AI Creation of a Digital Corps to bring skilled tech workers into government Founding of a Digital Service Academy: an accredited university providing subsidized education in exchange for a commitment to work for a time in government Include civil rights and civil liberty reports for new AI systems or major updates to existing systems Expanding allocations of employment-based green cards, and giving them to every AI PhD graduate from an accredited U.S. university Reforming the acquisition management system Department of Defense to make it faster and easier to introduce new technologies == Transparency == In December 2019, a ruling was made under the Freedom of Information Act (FOIA) that the NSCAI must also provide historical documents upon request. The Electronic Privacy Information Center (EPIC) filed the lawsuit against the NSCAI in September 2019 after being refused information about the upcoming meetings and prepared records of the commission under FOIA and the Federal Advisory Committee Act (FACA). The U.S. District Court for the District of Columbia ruled in June 2020 that the NSCAI must comply with FACA and therefore hold open meetings and provide records to the public. The lawsuit was also filed by EPIC.

    Read more →
  • Tactical NAV

    Tactical NAV

    Tactical NAV, also known as TACNAV-X, is a location-based tracking app designed for use by military personnel. The app is primarily designed to assist in pinpointing enemy fire and mapping waypoints. Tactical NAV also helps users efficiently relay critical information to tactical operations centers for prompt decision-making regarding airstrikes or medical evacuations. The TACNAV-X platform is intended to enhance situational awareness, refine navigation capabilities, and assist in tactical decision-making across various operational environments. == Overview == Tactical NAV allows users to pinpoint enemy fire. == History == Tactical NAV was designed by U.S. Army Captain Jonathan J. Springer, a Field Artillery officer serving as a Battalion Fire Support Officer (FSO) in the 101st Airborne Division. Springer conceived the idea for the app during his third tour in Afghanistan in support of Operation Enduring Freedom. On June 25, 2010, after a rocket attack by the Taliban killed two soldiers in his battalion, he was inspired to create an app that would prevent similar losses in the future, enhance situational awareness, and assist soldiers serving on combat deployments. In 2010, Springer founded TacNav Systems (formerly AppDaddy Technologies) to develop mobile applications for use by military personnel. He tested the app during combat operations in eastern Afghanistan and verified TACNAV-X's accuracy using DAGRs, AFATDS, Falcon View, CPOF, ATAK, and other approved Department of Defense (DoD) systems. As of 2012, the app had been downloaded 8,000 times.

    Read more →
  • AI Futures Project

    AI Futures Project

    The AI Futures Project is a nonprofit research organization based in the United States that specializes in forecasting the development and societal impact of advanced artificial intelligence. The organization is best known for its 2025 scenario forecast, AI 2027, which examines the potential near-term emergence of artificial general intelligence (AGI) and its possible global consequences. == History == The AI Futures Project was founded in 2025 by Daniel Kokotajlo, a former researcher in the governance division of OpenAI. Kokotajlo resigned from OpenAI in April 2024, expressing concerns that the company prioritized rapid product development over AI safety and was advancing without sufficient safeguards. He founded the nonprofit to conduct independent forecasting and policy research. The organization is registered as a 501(c)(3) nonprofit in the United States and is funded through donations. It operates with a small research staff and network of advisors drawn from fields including AI policy, forecasting, and risk analysis. == Activities == The mission of the AI Futures Project is to develop detailed scenario forecasts of the trajectory of advanced AI systems to inform policymakers, researchers, and the public. In addition to written reports, the group has conducted tabletop exercises and workshops based on its scenarios, involving participants from academia, technology, and public policy. == AI 2027 == In April 2025, the AI Futures Project released AI 2027, a detailed scenario forecast describing possible developments in AI between 2025 and 2027. The report was authored by Daniel Kokotajlo along with Eli Lifland, Thomas Larsen, and Romeo Dean, with editing assistance from blogger Scott Alexander. The scenario depicts very rapid progress in AI capabilities, including the development of autonomous AI systems capable of recursive self-improvement. AI 2027 presents two alternative endings: one in which international competition over advanced AI leads to catastrophic loss of human control, and another in which coordinated global action slows down development and averts imminent disaster. The authors emphasize that the narratives are hypothetical and intended as planning tools rather than literal forecasts. == Reception == AI 2027 attracted attention from technology journalists and AI researchers. Some commentators praised the report for its level of detail and its usefulness as a strategic planning exercise, while others criticized the scenario as implausibly aggressive in its timelines. The report was cited in policy discussions about AI governance. U.S. Vice President JD Vance reportedly read AI 2027 and referenced its warnings in conversations about international AI coordination. More recent reporting noted that the authors of AI 2027 had publicly revised some of their timelines. According to Kokotajlo, developments since the report's original publication suggested a slower path toward fully autonomous AI research systems than initially forecasted.

    Read more →
  • Stanford Research Institute Problem Solver

    Stanford Research Institute Problem Solver

    The Stanford Research Institute Problem Solver, known by its acronym STRIPS, is an automated planner developed by Richard Fikes and Nils Nilsson in 1971 at SRI International. The same name was later used to refer to the formal language of the inputs to this planner. This language is the base for most of the languages for expressing automated planning problem instances in use today; such languages are commonly known as action languages. This article only describes the language, not the planner. == Definition == A STRIPS instance is composed of: An initial state; The specification of the goal states – situations that the planner is trying to reach; A set of actions. For each action, the following are included: preconditions (what must be established before the action is performed); postconditions (what is established after the action is performed). Mathematically, a STRIPS instance is a quadruple ⟨ P , O , I , G ⟩ {\displaystyle \langle P,O,I,G\rangle } , in which each component has the following meaning: P {\displaystyle P} is a set of conditions (i.e., propositional variables); O {\displaystyle O} is a set of operators (i.e., actions); each operator is itself a quadruple ⟨ α , β , γ , δ ⟩ {\displaystyle \langle \alpha ,\beta ,\gamma ,\delta \rangle } , each element being a set of conditions. These four sets specify, in order, which conditions must be true for the action to be executable, which ones must be false, which ones are made true by the action and which ones are made false; I {\displaystyle I} is the initial state, given as the set of conditions that are initially true (all others are assumed false); G {\displaystyle G} is the specification of the goal state; this is given as a pair ⟨ N , M ⟩ {\displaystyle \langle N,M\rangle } , which specify which conditions are true and false, respectively, in order for a state to be considered a goal state. A plan for such a planning instance is a sequence of operators that can be executed from the initial state and that leads to a goal state. Formally, a state is a set of conditions: a state is represented by the set of conditions that are true in it. Transitions between states are modeled by a transition function, which is a function mapping states into new states that result from the execution of actions. Since states are represented by sets of conditions, the transition function relative to the STRIPS instance ⟨ P , O , I , G ⟩ {\displaystyle \langle P,O,I,G\rangle } is a function succ : 2 P × O → 2 P , {\displaystyle \operatorname {succ} :2^{P}\times O\rightarrow 2^{P},} where 2 P {\displaystyle 2^{P}} is the set of all subsets of P {\displaystyle P} , and is therefore the set of all possible states. The transition function succ {\displaystyle \operatorname {succ} } for a state C ⊆ P {\displaystyle C\subseteq P} , can be defined as follows, using the simplifying assumption that actions can always be executed but have no effect if their preconditions are not met: The function succ {\displaystyle \operatorname {succ} } can be extended to sequences of actions by the following recursive equations: succ ⁡ ( C , [ ] ) = C {\displaystyle \operatorname {succ} (C,[\ ])=C} succ ⁡ ( C , [ a 1 , a 2 , … , a n ] ) = succ ⁡ ( succ ⁡ ( C , a 1 ) , [ a 2 , … , a n ] ) {\displaystyle \operatorname {succ} (C,[a_{1},a_{2},\ldots ,a_{n}])=\operatorname {succ} (\operatorname {succ} (C,a_{1}),[a_{2},\ldots ,a_{n}])} A plan for a STRIPS instance is a sequence of actions such that the state that results from executing the actions in order from the initial state satisfies the goal conditions. Formally, [ a 1 , a 2 , … , a n ] {\displaystyle [a_{1},a_{2},\ldots ,a_{n}]} is a plan for G = ⟨ N , M ⟩ {\displaystyle G=\langle N,M\rangle } if F = succ ⁡ ( I , [ a 1 , a 2 , … , a n ] ) {\displaystyle F=\operatorname {succ} (I,[a_{1},a_{2},\ldots ,a_{n}])} satisfies the following two conditions: N ⊆ F {\displaystyle N\subseteq F} M ∩ F = ∅ {\displaystyle M\cap F=\varnothing } == Extensions == The above language is actually the propositional version of STRIPS; in practice, conditions are often about objects: for example, that the position of a robot can be modeled by a predicate A t {\displaystyle At} , and A t ( r o o m 1 ) {\displaystyle At(room1)} means that the robot is in Room1. In this case, actions can have free variables, which are implicitly existentially quantified. In other words, an action represents all possible propositional actions that can be obtained by replacing each free variable with a value. The initial state is considered fully known in the language described above: conditions that are not in I {\displaystyle I} are all assumed false. This is often a limiting assumption, as there are natural examples of planning problems in which the initial state is not fully known. Extensions of STRIPS have been developed to deal with partially known initial states. == A sample STRIPS problem == A monkey is at location A in a lab. There is a box in location C. The monkey wants the bananas that are hanging from the ceiling in location B, but it needs to move the box and climb onto it in order to reach them. Initial state: At(A), Level(low), BoxAt(C), BananasAt(B) Goal state: Have(bananas) Actions: // move from X to Y _Move(X, Y)_ Preconditions: At(X), Level(low) Postconditions: not At(X), At(Y) // climb up on the box _ClimbUp(Location)_ Preconditions: At(Location), BoxAt(Location), Level(low) Postconditions: Level(high), not Level(low) // climb down from the box _ClimbDown(Location)_ Preconditions: At(Location), BoxAt(Location), Level(high) Postconditions: Level(low), not Level(high) // move monkey and box from X to Y _MoveBox(X, Y)_ Preconditions: At(X), BoxAt(X), Level(low) Postconditions: BoxAt(Y), not BoxAt(X), At(Y), not At(X) // take the bananas _TakeBananas(Location)_ Preconditions: At(Location), BananasAt(Location), Level(high) Postconditions: Have(bananas) == Complexity == Deciding whether any plan exists for a propositional STRIPS instance is PSPACE-complete. Various restrictions can be enforced in order to decide if a plan exists in polynomial time or at least make it an NP-complete problem. == Macro operator == In the monkey and banana problem, the robot monkey has to execute a sequence of actions to reach the banana at the ceiling. A single action provides a small change in the game. To simplify the planning process, it make sense to invent an abstract action, which isn't available in the normal rule description. The super-action consists of low level actions and can reach high-level goals. The advantage is that the computational complexity is lower, and longer tasks can be planned by the solver. Identifying new macro operators for a domain can be realized with genetic programming. The idea is, not to plan the domain itself, but in the pre-step, a heuristics is created that allows the domain to be solved much faster. In the context of reinforcement learning, a macro-operator is called an option. Similar to the definition within AI planning, the idea is, to provide a temporal abstraction (span over a longer period) and to modify the game state directly on a higher layer.

    Read more →