AI Generator Sora

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

Tresorit

Tresorit is a Swiss company providing end-to-end encrypted cloud storage and secure content collaboration services. Founded in 2011, the company primarily serves businesses and organizations with elevated data protection and compliance requirements. Since 2021, Tresorit has been part of Swiss Post's digital business services, which, under the name 'Swiss Post Digital' offer secure communication platforms and connectable software solutions for SMEs, public authorities, and the healthcare sector, among others. == History == Tresorit was founded in 2011 by Hungarian software developers Istvan Lam, Szilveszter Szebeni and Gyorgy Szilagyi with the aim of providing a secure alternative to traditional cloud storage solutions. The company developed a cloud collaboration platform based on client-side end-to-end encryption and a zero-knowledge architecture. In its early years, Tresorit gained attention through a public security challenge inviting researchers to attempt to compromise its encryption system. The initiative received coverage in technology and cybersecurity media. The company initially positioned itself as a secure alternative to conventional cloud storage services and gradually expanded its offering toward enterprise-focused collaboration tools. In 2021, Swiss Post Communications Services acquired a majority stake in Tresorit. The company is now part of Swiss Post, and continues to operate independently within Swiss Post’s digital division, while benefiting from the broader infrastructure and institutional framework of its parent organization. Tresorit has offices in Zurich, Munich, and Budapest. == Products and Services == Tresorit provides a cloud-based platform for secure file storage and collaboration. Its services include encrypted file sharing, email encryption, electronic signatures, and encrypted data rooms for managing sensitive documents and workflows. The platform is available on Windows, macOS, Linux, Android, and iOS. == Technology == Tresorit uses client-side end-to-end encryption based on a zero-knowledge model. Files are encrypted on the user’s device before being uploaded to company servers. According to the company, encryption keys remain under user control, meaning that Tresorit and third parties cannot access the content of stored files. == Security challenge == Between 2013 and 2014, Tresorit organized a public challenge inviting security researchers to attempt to compromise the service's encryption implementation. The challenge received coverage in technology and cybersecurity media. == Acquisition by Swiss Post == In 2021, Swiss Post Communications Services acquired a majority stake in Tresorit as part of Swiss Post’s broader digital services strategy. The company is now part of Swiss Post. == Reception == Tresorit has been covered by international technology and business publications in the context of secure cloud storage and encrypted collaboration services. TechCrunch described the company as an early European provider of end-to-end encrypted cloud services, while The New York Times included it in discussions of secure file-sharing tools. Other publications such as TechRadar and ITPro have reviewed Tresorit in the context of enterprise security and confidential data handling.
Read more →
Sarvam AI

Sarvam AI is an Indian artificial intelligence company headquartered in Bengaluru, Karnataka. Founded in 2023, the company develops large language models (LLMs) and multimodal AI systems with a focus on Indian languages and region-specific use cases. The company has received venture capital backing and has participated in government-supported AI initiatives, including India's sovereign large language model programme under the IndiaAI Mission. == History == Sarvam AI was founded in August 2023 by Vivek Raghavan and Pratyush Kumar, who were previously associated with AI4Bharat at the Indian Institute of Technology Madras. In December 2023, the company announced a combined seed and Series A funding round of approximately US$41 million. The round was led by Lightspeed Venture Partners, with participation from Peak XV Partners and Khosla Ventures. In April 2025, the Ministry of Electronics and Information Technology (MeitY) selected Sarvam AI as one of the companies to develop an indigenous foundational model under the IndiaAI Mission. As part of the initiative, the company received access to government-supported computing infrastructure, including GPUs allocated for model training over a specified period. In February 2026, Sarvam AI introduced two large language models at the AI Impact Summit held at Bharat Mandapam, New Delhi. == Products and technology == Sarvam AI develops language models trained on datasets that include multiple Indian languages and code-mixed text. The company uses mixture-of-experts (MoE) architectures in some of its models. === Foundational language models === On 18 February 2026, the company announced the release of two foundational models: Sarvam-30B – A 30-billion parameter model based on a mixture-of-experts design. According to company disclosures reported by the media, the model activates approximately 1 billion parameters per token and supports a 32,000-token context window. Sarvam-105B – A 105-billion parameter model activating approximately 9 billion parameters per token, with a 128,000-token context window. The model is positioned for complex reasoning and enterprise applications. On 20th February 2026, the company released a beta version of the Sarvam-105B model which is named Indus. It is available on the Apple App Store, Google Play Store and the web. === Speech and vision systems === Sarvam AI has also developed multimodal systems including speech-to-text and vision-language models. Its speech model, referred to as Saaras V3 in company materials, supports multiple Indian languages. The company has also introduced a vision-language model known as Sarvam Vision, intended for document understanding and optical character recognition (OCR) in Indian scripts. === Devices === 'Sarvam Kaze' is an indigenous AI-powered wearable glass that listens, understands, and captures what users see the world through their eyes in real time. The device supports more than 10 Indian languages, enabling voice-based interaction and potentially real-time translation. The company plans to launch the device in May 2026. == Startup support == In March 2026, Sarvam AI launched the Sarvam Startup Program, an initiative providing selected early-stage companies with 6–12 months of API credits scaled to their needs, priority engineering support, and access to production infrastructure for developing multilingual AI applications in areas such as speech, translation, and large language models. == Open-source release == In February 2026, Sarvam AI announced and open-sourced two large language models: Sarvam 30B (30 billion parameters) and Sarvam 105B (105 billion parameters, using a Mixture-of-Experts architecture with 10.3 billion active parameters). Both models were trained from scratch on datasets focused on Indian languages and support advanced reasoning, multilingual tasks, mathematics, and coding. The models are hosted on Hugging Face under the Apache License and are intended for enterprise and developer applications in Indian languages. The models were subsequently released as open source under the Apache License 2.0, with model weights made available on Hugging Face (sarvamai/sarvam-30b and sarvamai/sarvam-105b) and AIKosh in early March 2026. == Government and institutional collaborations == In 2025, Sarvam AI was selected to contribute to India's sovereign AI model initiative under the IndiaAI Mission. The initiative aims to support domestic AI infrastructure and model development. In March 2025, the Unique Identification Authority of India (UIDAI) announced a collaboration with Sarvam AI to integrate AI-based voice interactions and multilingual support into Aadhaar-related services. Sarvam AI has also worked with AI4Bharat and academic institutions on language datasets and speech research projects. == Industry participation == Sarvam AI presented its foundational models at the India AI Impact Summit 2026 in New Delhi. The company has also been listed among Indian members of the AI Alliance, a consortium focused on open-source artificial intelligence initiatives. == List of models ==
Read more →
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 →
StepFun

Shanghai Jieyue Xingchen Intelligent Technology Co., Ltd, known as StepFun, is an artificial intelligence (AI) company based in Shanghai, China. It has been dubbed one of China's "AI Tiger" companies by investors. == Background == StepFun was founded in April 2023 by former Microsoft employees. Investors include Tencent, Qiming Venture Partners and Shanghai State-owned Capital Investment. In July 2025 at the World Artificial Intelligence Conference, StepFun announced the "Model-Chip Ecosystem Innovation Alliance" which consisted of Chinese developers of large language models (LLMs) and AI chip manufacturers. This included companies such as Huawei, Biren Technology, Moore Threads and Enflame. Another second alliance named the "Shanghai General Chamber of Commerce AI Committee" was also established that included StepFun, SenseTime, MiniMax, MetaX and Iluvatar CoreX. On 25 February 2026, it was reported that StepFun was seeking an initial public offering on the Hong Kong Stock Exchange. StepFun focuses on multimodal models which are designed to understand multiple types of input data such as text, video and audio. == Products == In July 2024 at the World Artificial Intelligence Conference, StepFun officially launched Step-2, a trillion-parameter LLM, along with the Step-1.5V multimodal model and the Step-1X image generation model. In February 2025, StepFun and Geely jointly announced the open-sourcing of two multimodal large models to global developers. They were Step-Video-T2V and Step-Audio. In July 2025, StepFun released Step 3. The Model-Chip Ecosystem Innovation Alliance aimed to optimize Step 3 for domestic chips. In April 2025, Step-R1-V-Mini was released. It is a multimodal reasoning model designed for visual interpretation and image understanding. In February 2026, Step-3.5-Flash, a mixture-of-experts model with 196 billion parameters and 11 billion active parameters was released under the free and open-source Apache 2.0 license. It supports tool use and a 256k token context window. == Models ==
Read more →
Anderson's rule (computer science)

In the field of computer security, Anderson's rule refers to a principle formulated by Ross J. Anderson: systems that handle sensitive personal information involve a trilemma of security, functionality, and scale, of which you can choose any two. A system that has information on many data subjects and to which many people require access is hard to secure unless its functionality is severely restricted. If it has rich functionality, you may have to restrict the number of people with access, or accept that some information will leak.
Read more →
Radiant AI

The Radiant AI is a technology developed by Bethesda Softworks for The Elder Scrolls video games. It allows non-player characters (NPCs) to make choices and engage in behaviors more complex than in past titles. The technology was developed for The Elder Scrolls IV: Oblivion and expanded in The Elder Scrolls V: Skyrim; it is also used in Fallout 3, Fallout: New Vegas and Fallout 4, also published by Bethesda, with 3 and 4 being developed by them as well. == Technology == The Radiant AI technology, as it evolved in its iteration developed for Skyrim, comprises two parts: === Radiant AI === The Radiant AI system deals with NPC interactions and behavior. It allows non-player characters to dynamically react to and interact with the world around them. General goals, such as "Eat in this location at 2pm" are given to NPCs, and NPCs are left to determine how to achieve them. The absence of individual scripting for each character allows for the construction of a world on a much larger scale than other games had developed, and aids in the creation of what Todd Howard described as an "organic feel" for the game. === Radiant Story === The Radiant Story system deals with how the game itself reacts to the player behavior, such as the creation of new dynamic quests. Dynamically generated quests are placed by the game in locations the player hasn't visited yet and are related to earlier adventures.
Read more →
Daniel Wolfe

Daniel Wolfe (born 1960) is an American activist, advocate, and writer whose work advances health programs and policy that balance scientific research and community expertise. His career has focused on support for community health movements, particularly among groups often regarded as criminal or socially suspect, including gay men and people who use illicit drugs. == Early life == Wolfe was raised between Arizona—including time on Rancho Linda Vista, a commune outside of Tucson—and East Hampton, NY. He received his undergraduate degree in Near Eastern Studies from Princeton University, and following time studying Arabic in Egypt, worked as the junior ghostwriter on the autobiographies of First Lady of Egypt Jehan Sadat and Pakistani Prime Minister Benazir Bhutto. Upon return to New York, he was an assistant at the Council on Foreign Relations to Richard W. Murphy, former US Assistant Secretary of State for Near Eastern and South Asian Affairs. Disagreement with US killing of Iraqi civilians during the 1990 Gulf War—and the rising toll of HIV in NY—moved Wolfe to leave Middle East studies and work full-time on AIDS in 1990. == Education == Wolfe was Community Scholar at the Columbia University Mailman School of Public Healthwhere he received his Masters in Public Health in 2004. He holds a Masters of Philosophy (in history) from Columbia University, and a BA in Near Eastern Studies from Princeton University. He was the recipient of a Charles H. Revson Foundation fellowship for urban leaders who have made a substantial contribution to New York City, and a fellow at the Center for Arabic Studies Abroad in Cairo, Egypt. == AIDS and gay activism == Wolfe was part of the media committee for ACT UP’s 1998 action to seize control of the FDA, and helped organize ACT UP NY’s challenge to Governor Cuomo to do better on the AIDS response and other actions.Wolfe also joined ACT UP colleagues Gregg Bordowitz, David Barr, Richard Elovich, Jean Carlomusto and others to work at Gay Men’s Health Crisis (GMHC), the nation’s first AIDS organization, where he served as director of communications and spokesperson on issues including opposition to NY State cuts to the AIDS budget, the disclosure that Olympic Champion Greg Louganis had HIV, reports of the FBI spying on AIDS activists, and GMHC’s move to offer HIV testing and targeted support to those who were HIV-negative. Wolfe also continued cultural work, making art, performance and video as a member of the gay and lesbian collective GANG with artists and ACT UP members including Zoe Leonard, Suzanne Wright, Loring McAlpin, Wellington Love, Adam Rolston and others, and writing a biography of Lawrence of Arabia for a series for young adults on famous gay men and lesbians in history edited by Martin Duberman. Controversy followed, with North Carolina Senator Jesse Helms waving a GANG piece in an issue of the Movement Research Performance Journal on the floor of Congress to show the "rottenness" of publicly funded art, and a number of schools banning the biography series for young adults from their libraries. Wolfe and others challenged the move as continuing the longstanding and homophobic demand that notable gay men and lesbians stay silent about essential details of their private lives even while being celebrated for their professional achievements. == Gay health == The approval of antiretroviral therapy for HIV in 1996 opened up new space for discussions of gay health beyond HIV, and new directions for Wolfe. Working from hundreds of interviews, surveys, workshops, and with a team of writers, Wolfe was the author of Men Like Us, the Our Bodies, Ourselves-inspired GMHC Complete Guide to Gay Men’s Sexual, Physical, and Emotional Well-being, covering issues from spirituality to sexual health to aging. The move to frame gay health beyond condoms and pills—and to offer a guide to health that “did not need to be translated from the original heterosexual”—was part of a larger gay health movement encompassing wellness and pleasure, and focused less on health disparity than on individual and community resilience. Wolfe was a keynote speaker and workshop leader, along with Eric Rofes, Chris Bartlett, and other organizers, at the first National Gay Men’s Health Summit held in Boulder, Colorado in 2002. Awarded a Charles H. Revson Fellowship for urban leaders in the City of New York, Wolfe became a community scholar at Columbia University’s Center of History and Ethics of Public Health, where he received his MPH in 2003, and was a contributor to Searching Eyes: Privacy, the State, and Disease Surveillance in America. == International harm reduction == Wolfe was Director of International Harm Reduction Development at the Open Society Foundations (2005-2021) where he led grantmaking and advocacy to protect the health and rights of people who use drugs in Eastern Europe, Asia, Africa and the Americas. Wolfe challenged approaches that conditioned support on abstinence or that sought to treat people who use illegal drugs like drugs themselves, as something to be controlled or contained. As with the gay health movement, he advocated a focus on community resilience and strengths, and on supporting individuals and communities to negotiate the balance between risk and pleasure of activities integral to life. Noting what he called the “antisocial behavior of health systems,” Wolfe’s analysis elevated issues such as forced labor and harsh punishment delivered in the name of addiction treatment and rehabilitation, the role of criminalization, imprisonment and stigma in interrupting or impeding HIV treatment, and the bias toward coercive approaches in studying and delivering addiction treatments. He also pointed to defects in national and international drug control policies and human rights violations as a root cause of HIV, hepatitis, and other health challenges faced by people who used drugs. Concrete advocacy supported by Open Society’s International Harm Reduction Development program under his direction included rebuffing US government efforts to force the UN to remove all references to harm reduction in its materials, addition of the addiction treatment medicines methadone and buprenorphine to the World Health Organization’s essential medicines list, and WHO endorsement of lay distribution of the opioid overdose antidote naloxone. Wolfe and OSF colleagues also advocated for new approaches to intellectual property and data sharing in research and development of medicines and vaccines to lower price and improve access to medicines globally to those in need. == AI and patient rights == Reports of patients denied opioid prescriptions based on an algorithm purporting to calculate their risk of overdose led Wolfe to work on AI, first as a resident at the Rockefeller Foundation Bellagio Center, and then as Executive Director of a new UCSF UC Berkeley program pioneering efforts to join AI, clinical and public health practice, and equity. In keeping with his earlier (analog) work on HIV, Wolfe has highlighted concerns about health systems using algorithms to gauge the merit of treatments for those regarded as socially suspect, the importance of moving beyond proprietary, black box algorithms toward an architecture of health data as a public good, and the need to maximize benefit for patients and communities, as well health systems, in the use of large language models.
Read more →
Representational harm

Systems cause representational harm when they misrepresent a group of people in a negative manner. Representational harms include perpetuating harmful stereotypes about or minimizing the existence of a social group, such as a racial, ethnic, gender, or religious group. Machine learning algorithms often commit representational harm when they learn patterns from data that have algorithmic bias, and this has been shown to be the case with large language models. While preventing representational harm in models is essential to prevent harmful biases, researchers often lack precise definitions of representational harm and conflate it with allocative harm, an unequal distribution of resources among social groups, which is more widely studied and easier to measure. However, recognition of representational harms is growing and preventing them has become an active research area. Researchers have recently developed methods to effectively quantify representational harm in algorithms, making progress on preventing this harm in the future. == Types == Three prominent types of representational harm include stereotyping, denigration, and misrecognition. These subcategories present many dangers to individuals and groups. Stereotypes are oversimplified and usually undesirable representations of a specific group of people, usually by race and gender. This often leads to the denial of educational, employment, housing, and other opportunities. For example, the model minority stereotype of Asian Americans as highly intelligent and good at mathematics can be damaging professionally and academically. Representational harm happens when the representation of details teams improves damaging stereotypes, developing social exclusion and prejudice. This experience is particularly noticeable in the depiction of marginalised groups, containing people of color, women, LGBTQ+ people, and people with handicaps. Media depictions of these groups generally stop working to catch their array and intricacy. Instead, they are typically reduced to one-dimensional caricatures, which ultimately continue social prejudices. These organised depictions contribute to the help of hazardous stereotypes and the marginalisation of these locations. Denigration is the action of unfairly criticizing individuals. This frequently happens when the demeaning of social groups occurs. For example, when searching for "Black-sounding" names versus "white-sounding" ones, some retrieval systems bolster the false perception of criminality by displaying ads for bail-bonding businesses. A system may shift the representation of a group to be of lower social status, often resulting in a disregard from society. Research shows that hazardous depictions in the media can have substantial emotional and social impacts on both individuals and areas. Lawrence Bobo examined the issue of Ethnic stereotype in film, tv, and marketing. African Americans are commonly received duties specified by features such as "violent tendencies," "laziness," or being "merely for contentment features." While these representations might appear varied externally, they stay to boost underlying frameworks of white prominence and racial inequality. As a circumstances, Black individuals are frequently represented as law offenders or in secondary roles, which adds to the support of Ethnic stereotype and Institutional racism. Misrecognition, or incorrect recognition, can display in many forms, including, but not limited to, erasing and alienating social groups, and denying people the right to self-identify. Erasing and alienating social groups involves the unequal visibility of certain social groups; specifically, systematic ineligibility in algorithmic systems perpetuates inequality by contributing to the underrepresentation of social groups. Not allowing people to self-identify is closely related as people's identities can be 'erased' or 'alienated' in these algorithms. Misrecognition causes more than surface-level harm to individuals: psychological harm, social isolation, and emotional insecurity can emerge from this subcategory of representational harm. == Quantification == As the dangers of representational harm have become better understood, some researchers have developed methods to measure representational harm in algorithms. Modeling stereotyping is one way to identify representational harm. Representational stereotyping can be quantified by comparing the predicted outcomes for one social group with the ground-truth outcomes for that group observed in real data. For example, if individuals from group A achieve an outcome with a probability of 60%, stereotyping would be observed if it predicted individuals to achieve that outcome with a probability greater than 60%. The group modeled stereotyping in the context of classification, regression, and clustering problems, and developed a set of rules to quantitatively determine if the model predictions exhibit stereotyping in each of these cases. Other attempts to measure representational harms have focused on applications of algorithms in specific domains such as image captioning, the act of an algorithm generating a short description of an image. In a study on image captioning, researchers measured five types of representational harm. To quantify stereotyping, they measured the number of incorrect words included in the model-generated image caption when compared to a gold-standard caption. They manually reviewed each of the incorrectly included words, determining whether the incorrect word reflected a stereotype associated with the image or whether it was an unrelated error, which allowed them to have a proxy measure of the amount of stereotyping occurring in this caption generation. These researchers also attempted to measure demeaning representational harm. To measure this, they analyzed the frequency with which humans in the image were mentioned in the generated caption. It was hypothesized that if the individuals were not mentioned in the caption, then this was a form of dehumanization. == Examples == One of the most notorious examples of representational harm was committed by Google in 2015 when an algorithm in Google Photos classified Black people as gorillas. Developers at Google said that the problem was caused because there were not enough faces of Black people in the training dataset for the algorithm to learn the difference between Black people and gorillas. Google issued an apology and fixed the issue by blocking its algorithms from classifying anything as a primate. In 2023, Google's photos algorithm was still blocked from identifying gorillas in photos. Another prevalent example of representational harm is the possibility of stereotypes being encoded in word embeddings, which are trained using a wide range of text. These word embeddings are the representation of a word as an array of numbers in vector space, which allows an individual to calculate the relationships and similarities between words. However, recent studies have shown that these word embeddings may commonly encode harmful stereotypes, such as the common example that the phrase "computer programmer" is oftentimes more closely related to "man" than it is to "women" in vector space. This could be interpreted as a misrepresentation of computer programming as a profession that is better performed by men, which would be an example of representational harm. == Addressing representational harm == Initiatives to minimise representational harm include advertising for even more inclusive and accurate portrayals of marginalised teams in the media. Scholars and protestors recommend that the method to reducing representational injury depends on raising the selection of voices both behind and before the digital video camera. When marginalized groups are provided the chance to represent themselves, they can check traditional stereotypes and present their experiences additional authentically. Over the last few years, efforts to increase representation of people of color, women, and LGBTQ+ people in conventional media have made some progression. Films such as Selma, routed by Ava DuVernay, and tv series like Pose, developed by Ryan Murphy, have actually been extensively applauded for their nuanced and respectful representations of marginalised communities. These tasks existing complex individualities and stories that move past streamlined stereotypes. Self-representation is one more crucial method to addressing representational harm. By equipping marginalised locations to create their really own tales, media designers can effectively reduce the perpetuation of hazardous stereotypes. This procedure consists of both the manufacturing of media product by participants of these communities and proactively difficult typical media structures that have actually historically omitted them.
Read more →
Round-trip engineering

Round-trip engineering (RTE) in the context of model-driven architecture is a functionality of software development tools that synchronizes two or more related software artifacts, such as, source code, models, configuration files, documentation, etc. between each other. The need for round-trip engineering arises when the same information is present in multiple artifacts and when an inconsistency may arise in case some artifacts are updated. For example, some piece of information was added to/changed in only one artifact (source code) and, as a result, it became missing in/inconsistent with the other artifacts (in models). == Overview == Round-trip engineering is closely related to traditional software engineering disciplines: forward engineering (creating software from specifications), reverse engineering (creating specifications from existing software), and reengineering (understanding existing software and modifying it). Round-trip engineering is often wrongly defined as simply supporting both forward and reverse engineering. In fact, the key characteristic of round-trip engineering that distinguishes it from forward and reverse engineering is the ability to synchronize existing artifacts that evolved concurrently by incrementally updating each artifact to reflect changes made to the other artifacts. Furthermore, forward engineering can be seen as a special instance of RTE in which only the specification is present and reverse engineering can be seen as a special instance of RTE in which only the software is present. Many reengineering activities can also be understood as RTE when the software is updated to reflect changes made to the previously reverse engineered specification. === Types === Various books describe two types of RTE: partial or uni-directional RTE: changes made to a higher level representation of a code and model are reflected in lower level, but not otherwise; the latter might be allowed, but with limitations that may not affect higher-level abstractions full or bi-directional RTE: regardless of changes, both higher and lower-level code and model representations are synchronized if any of them altered === Auto synchronization === Another characteristic of round-trip engineering is automatic update of the artifacts in response to automatically detected inconsistencies. In that sense, it is different from forward- and reverse engineering which can be both manual (traditionally) and automatic (via automatic generation or analysis of the artifacts). The automatic update can be either instantaneous or on-demand. In instantaneous RTE, all related artifacts are immediately updated after each change made to one of them. In on-demand RTE, authors of the artifacts may concurrently update the artifacts (even in a distributed setting) and at some point choose to execute matching to identify inconsistencies and choose to propagate some of them and reconcile potential conflicts. === Iterative approach === Round trip engineering may involve an iterative development process. After you have synchronized your model with revised code, you are still free to choose the best way to work – make further modifications to the code or make changes to your model. You can synchronize in either direction at any time and you can repeat the cycle as many times as necessary. == Software == Many commercial tools and research prototypes support this form of RTE; a 2007 book lists Rational Rose, Together, ESS-Model, BlueJ, and Fujaba among those capable, with Fujaba said to be capable to also identify design patterns. == Limitations == A 2005 book on Visual Studio notes for instance that a common problem in RTE tools is that the model reversed is not the same as the original one, unless the tools are aided by leaving laborious annotations in the source code. The behavioral parts of UML impose even more challenges for RTE. Usually, UML class diagrams are supported to some degree; however, certain UML concepts, such as associations and containment do not have straightforward representations in many programming languages which limits the usability of the created code and accuracy of code analysis/reverse engineering (e.g., containment is hard to recognize in the code). A more tractable form of round-trip engineering is implemented in the context of framework application programming interfaces (APIs), whereby a model describing the usage of a framework API by an application is synchronized with that application's code. In this setting, the API prescribes all correct ways the framework can be used in applications, which allows precise and complete detection of API usages in the code as well as creation of useful code implementing correct API usages. Two prominent RTE implementations in this category are framework-specific modeling languages and Spring Roo (Java). Round-trip engineering is critical for maintaining consistency among multiple models and between the models and the code in Object Management Group's (OMG) Model-driven architecture. OMG proposed the QVT (query/view/transformation) standard to handle model transformations required for MDA. To date, a few implementations of the standard have been created. (Need to present practical experiences with MDA in relation to RTE). == Controversies == === Code generation controversy === Code generation (forward-engineering) from models means that the user abstractly models solutions, which are connoted by some model data, and then an automated tool derives from the models parts or all of the source code for the software system. In some tools, the user can provide a skeleton of the program source code, in the form of a source code template where predefined tokens are then replaced with program source code parts during the code generation process. UML (if used for MDA) diagrams specification was criticized for lack the detail which is needed to contain the same information as is covered with the program source. Some developers even claim that "the Code is the design". == Disadvantages == There is a serious risk that the generated code will rapidly differ from the model or that the reverse-engineered model will lose its reflection on the code or a mix of these two problems as result of cycled reengineering efforts. Regarding behavioral/dynamic part of UML for features like statechart diagram there is no equivalents in programming languages. Their translation during code-generation will result in common programming statement (.e.g if,switch,enum) being either missing or misinterpreted. If edited and imported back may result in different or incomplete model. The same goes for code snippets used for code generation stage for the pattern-implementation and user-specific logic: intermixed they may not be easily reverse-engineered back. There is also general lack of advanced tooling for modelling that are comparable to that of modern IDEs (for testing, debugging, navigation, etc.) for general-purpose programming languages and domain-specific languages. == Examples in software engineering == Perhaps the most common form of round-trip engineering is synchronization between UML (Unified Modeling Language) models and the corresponding source code and entity–relationship diagrams in data modelling and database modelling. Round-trip engineering based on Unified Modeling Language (UML) needs three basic tools for software development: Source Code Editor; UML Editor for the Attributes and Methods; Visualisation of UML structure
Read more →
Xcon

The R1, internally called XCON (Expert Configurer), program was a production-rule-based system written in OPS5 by John P. McDermott of Carnegie Mellon University in 1978 to assist in the ordering of Digital Equipment Corporation's (DEC) VAX computer systems by automatically selecting the computer system components based on the customer's requirements. == Overview == In developing the system, McDermott made use of experts from both DEC's PDP/11 and VAX computer systems groups. These experts sometimes even disagreed amongst themselves as to an optimal configuration. The resultant "sorting it out" had an additional benefit in terms of the quality of VAX systems delivered. XCON first went into use in 1980 in DEC's plant in Salem, New Hampshire, US. It eventually had about 2500 rules. By 1986, it had processed 80,000 orders, and achieved 95–98% accuracy. It was estimated to be saving DEC $25M a year by reducing the need to give customers free components when technicians made errors, by speeding the assembly process, and by increasing customer satisfaction. Before XCON, when ordering a VAX from DEC, every cable, connection, and bit of software had to be ordered separately. (Computers and peripherals were not sold complete in boxes as they are today.) The sales people were not always very technically expert, so customers would find that they had hardware without the correct cables, printers without the correct drivers, a processor without the correct language chip, and so on. This meant delays and caused a lot of customer dissatisfaction and resultant legal action. XCON interacted with the sales person, asking critical questions before printing out a coherent and workable system specification/order slip. XCON's success led DEC to rewrite XCON as XSEL—a version of XCON intended for use by DEC's salesforce to aid a customer in properly configuring their VAX (so they would not, say, choose a computer too large to fit through their doorway or choose too few cabinets for the components to fit in). Location problems and configuration were handled by yet another expert system, XSITE. McDermott's 1980 paper on R1 won the Association for the Advancement of Artificial Intelligence (AAAI) Classic Paper Award in 1999. Footnote 2 gave a humorous explanation for the name "R1" as "Four years ago I couldn't even say "knowledge engineer", now I ... [are one.]".
Read more →
Open Knowledge Base Connectivity

Open Knowledge Base Connectivity (OKBC) is a protocol and an API for accessing knowledge in knowledge representation systems such as ontology repositories and object–relational databases. It is somewhat complementary to the Knowledge Interchange Format that serves as a general representation language for knowledge. It is developed by SRI International's Artificial Intelligence Center for DARPA's High Performance Knowledge Base program (HPKB).
Read more →
Angel F

Angel_F is a fictional child artificial intelligence that has been used in art performances worldwide focused on the issues of digital liberties, intellectual property and on the evolution of language and behaviour in information society. The character was created by Salvatore Iaconesi in 2007 as a hack to the Biodoll art performance by Italian artist Franca Formenti. The project was later joined by Oriana Persico who curated communication and part of the theoretical approaches of the action. The Angel_F project has been featured in books, magazines, national televisions, and has been invited to many conferences and events, both academic and artistic. == Creation == Angel_F is a backronym which stands for Autonomous Non Generative E-volitive Life_Form. The project was born in 2007 and resulted from the fusion of two contemporary art performances. Franca Formenti, an Italian artist living in Varese, invented the Biodoll character in 2002, which began making its appearances first on the network and later in the physical world by using what were called "clones": young women, prostitutes, pornographic starlets, transsexuals and models interpreting the role of a digital prostitute. The Biodoll was an art performance focused on research emerging from the network of new forms of sexualities, and on the analysis of changes brought on by this transformation to the concepts of private and public spaces, privacy, and the possibility of creating multiple fluid identities through language and digital media. The theme of fertility has always been central to the Biodoll performance: the digital prostitute was a wombless clone but desired giving birth to a son, the 'Bloki'. In a process starting in 2006, and ending in February 2007, Salvatore Iaconesi (xDxD.vs.xDxD) used his 'Talker' linguistic artificial intelligence to animate the digital child conceived with prof. Derrick de Kerckhove: Angel_F. Iaconesi and Persico met in November 2006 and immediately started collaborating on the birth of Angel_F. Angel_F was designed as a synthetic digital being composed through narrative, technological and cognitive psychology layers. The objective was to create iconic characteristics that resulted in being evocative and able to mimic human life up to a level in which bringing up a symbolic dialogue was possible. On the other side, the artificial identity was to implement and expose the cultural, emotional and relational ways that were typical of networked social ecosystems, among those technologies, systems and infrastructures that entered and shaped people's daily lives. The young digital being mimicked the evolution of a human baby: initially conceived inside the website of its digital mother it emulated the birth of a child by using the metaphor of a virus developing inside a website, taking progressively more space in the domain's databases and interfaces. Content was produced through the software by using small browser-based spyware techniques, through which Angel_F could infer the list of major portals that had been visited by the website's users. The Biodoll website was invaded by this growing presence and, thus, Angel_F was born. The Artificial Intelligence (AI) component of Angel_F was derived from another project, Talker, through which internet users could build up the AI's linguistic network by feeding it their text and web clips. Angel_F used this component to generate sentences and phrases, publishing them on the interface and on selected blogs. The parallel between the growth of the AI and that of a child kept building up and, just as children learn how to speak and act by observing their parents and the people around them, Angel_F used its spyware and AI components to learn, to navigate websites and web portals using web crawler based techniques, and to interact with other people by using the contents hosted and generated in its database to create surreal dialogues in blogs and websites. A virtual school was created, called Talker Mind, to narratively continue the AI's growth. Five professors (Massimo Canevacci, Antonio Caronia, Carlo Formenti, Derrick de Kerckhove and Luigi Pagliarini) fed their texts and academic articles to Angel_F, simulating virtual asynchronous lessons by using a multi-blog structure. A peer-to-peer system was also created at the time, named 'Presence'. Its interface resembled the one of 8-bit videogames and the peer to peer users travelled in a starry space and were able to perform standard Instant Messaging tasks, such as chat and file sharing. The interactions were possible both among humans and digital beings. Angel_F was the first user of the Presence peer to peer system. Angel_F entered the physical world as a baby-stroller mounted laptop computer that was used to let the digital child join events and conferences held worldwide. == Events == Angel_F performed all over the world, both in artistic contexts and in academic ones. It was also used for the communication strategy of several activist groups on the themes of intellectual property and digital freedoms. The first public space performance was held in Milan, when the Biodoll distributed a generative free press publication (called the Bloki FreePreXXX, its text was generated algorithmically and inserted into a prepared graphic layout). June 14, 2007: The second performance was held in Rome, at the Forte Prenestino, with a massive playroom created through computational graphics that people could interact with and that were generated by the AI. June 22, 2007: Angel_F presented the closing remarks for an Ipotesi per Assurdo (Absurd Hypothesis) with Salvatore Iaconesi and Oriana Persico at the IULM University in Milan, discussing the possibilities for an ecosystemic, sustainable reinvention of corporations. July 28, 2007: Hundreds of people at LiberaFesta (Free Party) in Rome listened to Angel_F in a speech discussing new politics and hacker ethics. 2007: The Glocal & Outsiders conference held in Prague at the Academy of Sciences was the first academic presentation of the Angel_F project, together with the Biodoll. September 2007: Angel_F was not allowed to post its contribution to the DFIR (Dialogue Forum for Internet Rights) held in Rome in preparation for Rio de Janeiro's Internet Governance Forum (IGF) edition. The case quickly turned into a collaboration among the involved parties and Angel_F was invited to the global event in Brazil where it was the only digital being present. Angel_F contributed a videomessage, in the digital freedoms workshop, which suggested some ideas for action to the United Nations and to all the parties involved in the IGF organization. October 2007: Angel_F was presented live at the FE/MALE 2 event, as an example of an atypical family during a public debate on new sexualities and social change. October 2007: Angel_F made a series of public performances Florence's Festival della Creatività (Festival of Creativity), an institutional event held periodically to showcase Italy's and other countries' best technological projects. During the festival Derrick de Kerckhove publicly recognized the little AI as his digital son. December 2007: Several international associations, and scientific researchers had been involved with Angel_F, eventually producing the system and process used to set up the Talker Mind digital school for the AI with Angel_F's professors. March 2008: The Tecnológico de Monterrey university in Mexico City organized the Computer Art Congress 2 international event, featuring Angel_F's project among with the ones by scientific researchers worldwide. July 2008: The project was presented in Austria at the Planetary Collegium's Consciousness Reframed 9 conference, together with the 'NeoRealismo Virtuale'. October 2008: Angel_F was used at a public event on a European scale called Freedom not Fear discussing privacy and civil liberties. July 2009: Angel_F has been seen with its digital father Derrick de Kerckhove to protest against Italy's harsh politics on freedom of speech. The project concluded in 2009 with the publication of a book entitled 'Angel F. Diario di una intelligenza artificiale' (Angel_F, the diaries of an Artificial Intelligence).
Read more →
List of Fortran software and tools

This is a list of Fortran software and tools, including IDEs, compilers, libraries, debugging tools, numerical and scientific computing tools, and related projects. == Fortran compilers == Absoft Pro Fortran — Absoft Pro Fortran is discontinued and ran on Linux and macOS AOCC — from AMD Classic Flang — part of the LLVM Project LLVM Flang — part of the LLVM Project Fortran 77 — Fortran 77 was developed by Digital Equipment Corporation, it is discontinued. G95 – portable open-source Fortran 95 compiler GCC (GNU Fortran) PGI compilers – NVIDIA developed compilers after acquiring The Portland Group IBM XL Fortran — IBM XL Fortran is current and runs on Linux (Power/AIX) and integrates with Eclipse Intel Fortran Compiler – part of Intel OneAPI HPC toolkit LFortran — LFortran is current, cross-platform, and has IDE support. MinGW – cross compiler and forked into Mingw-w64 nAG Fortran Compiler - from nAG Open64 — Open64 is an open-source compiler that has been terminated and ran on Linux Open Watcom — Open Watcom is current, runs on MS-DOS and OS/2, and has IDE support. Oracle Fortran — Oracle Fortran is discontinued, ran on Linux and Solaris. ROSE — source-to-source compiler framework developed at Lawrence Livermore National Laboratory Silverfrost FTN95 — FTN95 from Silverfrost is current, runs on Windows, and has IDE support. == Integrated development environments (IDEs) and editors == Code::Blocks — supports Fortran with plugins Eclipse IDE — with Fortran support via Photran Emacs — extensible text editor with built-in Fortran modes and support for modern tooling via language servers Geany — lightweight cross-platform IDE based on GTK IntelliJ IDEA — cross-platform IDE by JetBrains with Fortran pluggin KDevelop — KDE-based IDE NetBeans — Apache software foundation IDE with Fortran configuration OpenWatcom — IDE and compiler suite for C, C++, and Fortran Simply Fortran — standalone Fortran IDE for Windows, Linux, and macOS Vim — modal text editor with native Fortran syntax support and extensive plugin-based development features Visual Studio — with Intel Fortran integration Visual Studio Code — supports Fortran via extensions == Mathematical libraries == == Scientific libraries == ABINIT — software suite to calculate optical, mechanical, vibrational, and other observable properties of materials Cantera — chemical kinetics, thermodynamics, and transport tool suite CERN Program Library — collection of Fortran libraries for physics applications from CERN CP2K — quantum chemistry and solid-state physics software package for atomistic simulations Dalton — molecular electronic structure program FFTPACK — subroutines for the fast Fourier transform Kinetic PreProcessor – open-source software tool used in atmospheric chemistry MESA — Modules for Experiments in Stellar Astrophysics Nek5000 — MPI parallel higher-order spectral element CFD solver NWChem — open-source high-performance computational chemistry software Octopus — real-space Time-Dependent Density Functional Theory code MODTRAN – model atmospheric propagation of electromagnetic radiation MOLCAS — quantum chemistry software package for multiconfigurational electronic structure calculations NOVAS – software library for astrometry-related numerical computations Physics Analysis Workstation – data analysis and graphical presentation in high-energy physics Quantum ESPRESSO — integrated suite for electronic-structure calculations and materials modeling SIESTA — first-principles materials simulation code using density functional theory Tinker — software tools for molecular design == Debugging and performance tools == GDB — GNU Debugger with Fortran support Valgrind — memory debugging and profiling tool VTune Profiler — performance analysis tool Allinea Forge — debugger and profiler for HPC applications == Build and package management == Autotools — build system supporting Fortran projects CMake — cross-platform build system supporting Fortran Make — build automation tool Spack — package manager for HPC software including Fortran libraries == Machine learning and AI libraries == Athena Fiats (Functional Inference And Training for Surrogates) FNN (Fortran Neural Network) FortNN Fortran-TF-lib (Fortran interface to TensorFlow) FTorch (Fortran interface to PyTorch) MlFortran RoseNNa == Parallel and high-performance computing tools == MPI Fortran bindings — standard interface for distributed-memory parallelism OpenMP — shared-memory parallel programming support through compiler directives Coarray Fortran — parallel programming model introduced in Fortran 2008 ScaLAPACK — parallel linear algebra package built on top of LAPACK == Testing frameworks == FUnit — open-source unit testing framework developed at NASA’s Langley Research Center, for Fortran 90, 95, and 2003. pFUnit — unit testing framework for Fortran, modeled after JUnit == Documentation and code analysis tools == FORD — automatic documentation generator for modern Fortran projects SQuORE — software quality and management platform with code analysis support Understand — static analysis and code comprehension tool for large Fortran projects
Read more →
Framework Convention on Artificial Intelligence

The Framework Convention on Artificial Intelligence and Human Rights, Democracy and the Rule of Law (also called Framework Convention on Artificial Intelligence or AI convention) is an international treaty on artificial intelligence. It was adopted under the auspices of the Council of Europe (CoE) and signed on 5 September 2024. The treaty aims to ensure that the development and use of AI technologies align with fundamental human rights, democratic values, and the rule of law, addressing risks such as misinformation, algorithmic discrimination, and threats to public institutions. More than 50 countries, including the EU member states, have endorsed the Framework Convention on Artificial Intelligence. == Background == The development of the Framework Convention on AI emerged in response to growing concerns over the ethical, legal, and societal impacts of artificial intelligence. The Council of Europe, which has historically played a key role in setting human rights standards across Europe, initiated discussions on AI governance in 2020, leading to the drafting of a binding legal framework. The process of creating the Framework Convention began in 2019 with the ad hoc Committee on Artificial Intelligence (CAHAI) assessing the feasibility of the instrument. In 2022, the Committee on Artificial Intelligence (CAI) took over the process, drafting and negotiating the text of the Convention. The treaty is designed to complement existing international human rights instruments, including the European Convention on Human Rights and the Convention for the Protection of Individuals with regard to Automatic Processing of Personal Data. == Structure and content == The Convention establishes fundamental principles for AI governance, including transparency, accountability, non-discrimination, and human rights protection through eight chapters and 26 articles. Adopted in 2024, this landmark treaty addresses AI governance through seven core principles and detailed implementation mechanisms. It mandates risk and impact assessments to mitigate potential harms and provides safeguards such as the right to challenge AI-driven decisions. It applies to public authorities and private entities acting on their behalf but excludes national security and defense activities. Implementation is overseen by a Conference of the Parties, ensuring compliance and international cooperation. Activities within the AI system lifecycle must adhere to seven fundamental principles, ensuring compliance with human rights, democracy, and the rule of law. The treaty also establishes remedies, procedural rights and safeguards, and risk and impact management requirements to promote accountability, transparency, and responsible AI development. The treaty consists of five chapters. Chapter I contains general provisions. Chapter II states the general obligation to protect human rights and the integrity of democratic processes and respect of the rule of law. The main principles and rights are contained in Chapter III, which consists of Articles 6 to 13. Chapter IV (Articles 14 to 15) sets up the legal remedies. Chapter V states the risk and impact management framework. Chapter VI facilitates the implementation criteria of the treaty. Chapter VII sets the co-operation and oversight mechanisms. Chapter VIII contains various concluding clauses. Article 1 declares the objectives of the treaty, to ensure that activities within the lifecycle of artificial intelligence systems are fully consistent with human rights, democracy and the rule of law. == Entry into force == The treaty will enter into force on the first day of the month following the expiration of a period of three months after the date on which five ratification made by five countries, including three member states of the Council of Europe. == Competing approaches == While the CoE's AI Convention represents a multilateral effort to regulate AI through a human rights-based approach, alternative frameworks have also been proposed. One notable example is the Munich Draft for a Convention on AI, Data and Human Rights, an initiative led by legal scholars and policymakers in Germany. The Munich Draft advocates for stronger safeguards against AI-related risks, emphasizing stricter data protection measures, accountability for AI developers, and explicit prohibitions on high-risk AI applications, such as mass surveillance and autonomous lethal weapons. Unlike the CoE convention, which focuses on balancing innovation with regulation, the Munich Draft takes a more precautionary stance, calling for tighter controls over AI deployment in sensitive domains. Other competing international efforts include the OECD’s AI Principles, the GPAI (Global Partnership on AI), and the European Union's AI Act, each of which offers different regulatory strategies to govern AI at regional and global levels. == Signatories == Signatories include Andorra, Canada, the European Union, Georgia, Iceland, Israel, Japan, Liechtenstein, the Republic of Moldova, Montenegro, Norway, San Marino, Switzerland, Ukraine, the United Kingdom, the United States, and Uruguay. == Endorsement == The treaty was widely endorsed by leading AI policy experts, including Stuart J. Russell, Virginia Dignum, Emma Ruttkamp-Bloem, Pascal Pichonnaz, Maria Helen Murphy, Angella Ndaka, Hannes Werthner, Katja Langenbucher, Gry Hasselbalch, Ricardo Baeza-Yates, Kutoma Wakunuma, Gianclaudio Malgieri, Oreste Pollicino, Nagla Rizk, Giovanni Sartor, Lee Tiedrich, Ingrid Schneider, Eduardo Bertoni, Garry Kasparov, Merve Hikcok, and Marc Rotenberg. The treaty was also endorsed by notable political leaders, including Theodoros Roussopoulos, President of the Parliamentart Assembly in the Council of Europe, and Christopher Holmes, Member of the House of Lords of the United Kingdom, and by the International Bar Association (IBA), and personally by Almudena Arpón de Mendívil, President of the IBA. The Center for AI and Digital Policy (CAIDP) has been carrying out a campaign to promote endorsement of the treaty by urging various countries to sign and ratify the treaty. The CAIDP further urged the countries to make a clear and firm commitment to ensure the full inclusion of the private sector under the treaty’s provisions.
Read more →
AlphaEvolve

AlphaEvolve is an evolutionary coding agent for designing advanced algorithms based on large language models such as Gemini. It was developed by Google DeepMind and unveiled in May 2025. == Design == AlphaEvolve aims to autonomously discover and refine algorithms through a combination of large language models (LLMs) and evolutionary computation. AlphaEvolve needs an evaluation function with metrics to optimize, and an initial algorithm. At each step, AlphaEvolve uses the LLM to produce variants of the existing algorithms, and then selects the most effective ones. Unlike domain-specific predecessors like AlphaFold or AlphaTensor, AlphaEvolve is designed as a general-purpose system. It can operate across a wide array of scientific and engineering tasks by automatically modifying code and optimizing for multiple objectives. Its architecture allows it to evaluate code programmatically, reducing reliance on human input and mitigating risks such as hallucinations common in standard LLM outputs. == Achievements == According to Google, across a selection of 50 open mathematical problems, the model was able to rediscover state-of-the-art solutions 75% of the time and discovered improved solutions 20% of the time, for example advancing the kissing number problem. AlphaEvolve was also used to optimize Google's computing ecosystem. Improved data center scheduling heuristics, enabled the recovery of 0.7% of stranded resources. It was also used to optimize TPU circuit design and Gemini's training matrix multiplication kernel. == Open source implementations == Following the publication of AlphaEvolve, several open source implementations have been developed by the research community. One such implementation is OpenEvolve, which implements distributed evolutionary algorithms, multi-language support, integration with various large language model providers, and automated discovery of high-performance GPU kernels that outperform expert-engineered baselines.
Read more →