AI Data Analyst Zalando

AI Data Analyst Zalando — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Boris FX

Boris FX is a visual effects, video editing, photography, and audio software plug-in developer based in Miami, Florida, USA. The developer is known for its flagship products, Continuum (formerly Boris Continuum Complete/BCC), Sapphire, Mocha, and Silhouette. Boris FX creates plug-in tools for feature film, broadcast television, and multimedia post-production workflows. The plug-ins are compatible with various NLEs, including Adobe After Effects and Premiere Pro, Avid Media Composer, Apple Final Cut Pro, and OFX hosts such as Autodesk Flame, Foundry Nuke, Blackmagic Design DaVinci Resolve and Fusion, and VEGAS Pro. Boris FX has incorporated artificial intelligence into its software, introducing features for noise reduction, rotoscoping, upscaling, and masking. The company has acquired technologies via mergers and acquisitions from Imagineer Systems, GenArts, Silhouette FX, Digital Film Tools, CrumplePop and Andersson Technologies to expand its visual effects, editing, photography, and audio tools. == History == Boris FX was founded in 1995 by Boris Yamnitsky. The former Media 100 engineer (a member of the original Media 100 launch team in 1993) released “Boris FX,” the first plug-in-based digital video effects (DVE) for Adobe Premiere and Media 100, in 1995. The plug-in won Best of Show at Apple Macworld in Boston, MA that same year. The Boris FX Suite includes a range of visual effects and post-production tools, such as Sapphire, Continuum, Mocha Pro, Silhouette, SynthEyes, CrumplePop, Optics, and Particle Illusion. == Media 100 == In October 2005, Yamnitsky acquired Media 100 the company that launched his plug-in career. Boris FX had a long relationship with Media 100 which bundled Boris RED software as its main titling and compositing solution. Media 100's video editing software is available as freeware for macOS. == Continuum == Continuum is a visual effect and compositing plugin suite that includes a library of over 300 effects and more than 40 transitions, including tools for image restoration, compositing, titling, particle generation, and stylized effects, along with features such as lens flares, lighting effects, and cinematic color grading presets. A key component of Continuum is its integration with the Mocha planar tracking and masking system, enabling advanced tracking and rotoscoping within the effects. The suite also includes Particle Illusion, a real-time particle generator used for creating visual effects such as explosions, smoke, and abstract motion graphics, as well as Primatte Studio, a chroma keying and compositing toolset for green screen and blue screen workflows. Continuum supports GPU acceleration and offers compatibility with HDR and 360/VR content. Regular updates introduce new effects, presets, and performance enhancements to expand its capabilities. In October 2018, Continuum relaunched Particle Illusion, a Mocha Essentials workflow with magnetic edge-snapping, and updates to Title Studio. In October 2019, Continuum introduced Corner Pin Studio with built-in Mocha tracking for quick screen replacement and inserts, 6 stylized transitions, and 4 creative effects. In October 2020, Continuum released an update that included over 80 GPU-accelerated effects such as film stocks, color grades, optical filter simulations, and a digital gobo library. The update also introduced a custom FX Editor interface, real-time particles, and more than 1,000 drag-and-drop presets. In November 2021, it added multi-frame rendering for After Effects, native Apple M1 support, fluid dynamics in Particle Illusion, and 60 color-grade presets. In October 2022, the software introduced 10 additional transitions, a revised Particle Illusion workflow, an atmospheric glow effect, and more than 250 curated presets. Continuum plugins have been used in television, streaming, and film projects, including A Black Lady Sketch Show (HBO/HBO Max), Star Trek: Discovery (CBS), Andor (Disney+), The Curse of Oak Island (History Channel), Keeping up with the Kardashians (E!), This Old House (PBS), Ms. Marvel (Disney+), MasterChef (Fox), WipeOut (TBS), The Boys (Prime Video), and The Today Show (NBC). == Mocha Pro == In December 2014, Boris FX merged with Imagineer Systems, the UK-based developer of the Academy Award-winning planar motion tracking software, Mocha Pro. Mocha Pro's features include planar tracking (motion tracking), rotoscoping, image stabilization, 3D camera tracking, and object removal. In June 2016, Mocha released (v5) which introduced Mocha Pro's tools as plug-ins for Adobe After Effects and Premiere Pro, Avid Media Composer, and OFX hosts Foundry's NUKE, Blackmagic Design Fusion, VEGAS Pro, and HitFilm. A simplified version, Mocha AE, is included with Adobe After Effects Creative Cloud and has been bundled with the software since CS4. A similar version is also available with HitFilm Pro from FXhome and VEGAS Pro. Mocha's tracking SDK is integrated into other visual effects tools, including SAM Quantel Pablo Rio, Silhouette FX, CoreMelt, and Motion VFX. Mocha Pro has been used in various film and television productions, including Birdman, Black Swan, the Harry Potter series, The Hobbit, Star Wars, The Mandalorian, Star Trek: Discovery, and The Umbrella Academy. It has also been employed in projects such as Gone Girl, The Hunger Games: Mockingjay – Part 1, Game of Thrones, and House of Cards. == Sapphire == GenArts, founded by Karl Sims in 1996, developed visual effects plug-ins that were used by studios and post-production facilities. In September 2016, Boris FX merged with former competitor, GenArts, Inc., developer of Sapphire high-end visual effects plug-ins, to expand its suite of motion graphics and VFX tools. The merger brought Sapphire alongside Boris Continuum Complete (BCC) and Mocha Pro, integrating these tools for film and television post-production. The Sapphire suite includes a library of over 270 effects and transitions, organized into categories such as lighting, stylization, distortions, textures, and transitions. Commonly used effects include glows, lens flares, film looks, and blurs. The plug-ins are designed to be GPU-accelerated, allowing for improved rendering performance and real-time previews in supported host applications. A central feature of Sapphire is the Builder tool, a node-based workspace that allows users to create custom effects and transitions by combining multiple Sapphire plug-ins. This enables a high level of creative flexibility and reusability, making it a popular tool for both editors and VFX artists. Sapphire also integrates with Mocha, Boris FX's planar tracking and masking system, allowing for advanced control of visual elements within an effect. In October 2017, Boris FX released its first new version of Sapphire since the GenArts acquisition. Sapphire (v11) now includes integrated Mocha tracking and masking tools. Sapphire is available for Adobe, Avid, the Autodesk Flame family, and OFX hosts including Blackmagic DaVinci Resolve and Fusion, and Foundry's NUKE. As part of the merger, Boris FX acquired the rights to Particle Illusion. In 2018, Boris FX reintroduced the product to the larger NLE/Compositing market. Sapphire's plug-ins transitioned from C to C++ to improve performance and support higher-resolution visual effects. This update enhanced floating-point calculations, compatibility with film editing APIs, and integration with NVIDIA's CUDA for faster rendering. The plug-ins have been used in various films, including Avatar, the Harry Potter and the Prisoner of Azkaban, Iron Man, The Lord of the Rings, The Matrix trilogy, Titanic, and X-Men. == Particle Illusion == As part of the merger with GenArts in 2016, Boris FX acquired the rights to the Particle Illusion (formerly particleIllusion) product, a storied particle system from the original developer Alan Lorence, the founder of Wondertouch. In 2018, Boris FX released a redesigned version of the product to a larger NLE/compositing market as part of Continuum (2019). The new Particle Illusion plug-in supports Adobe, Avid, and many OFX hosts. == Silhouette == In September 2019, Boris FX merged with SilhouetteFX, Academy Award-winning developer of Silhouette, a high-end digital paint, advanced rotoscoping, motion tracking, and node-based compositing application for visual effects in film post-production. The acquisition integrated Silhouette's advanced rotoscoping and paint technology, recognized by the Academy of Motion Pictures, into Boris FX's suite of products, alongside Sapphire, Continuum, and Mocha Pro. In May 2021, Boris FX released Silhouette 2021, the first version of Silhouette released by Boris FX to function both as a standalone application and as a plug-in for Adobe, Autodesk, Nuke, and other OFX hosts. Silhouette has been used in the visual effects of films such as Avatar, Avengers: Infinity War, Blade Runner 2049, Ex Machina, and Interstellar. == Optics == In June 2020, Boris FX launched Optics, its first plugin deve
Read more →
Shakey the robot

Shakey the Robot was the first general-purpose mobile robot able to reason about its own actions. While other robots would have to be instructed on each individual step of completing a larger task, Shakey could analyze commands and break them down into basic chunks by itself. Due to its nature, the project combined research in robotics, computer vision, and natural language processing. Because of this, it was the first project that melded logical reasoning and physical action. Shakey was developed at the Artificial Intelligence Center of Stanford Research Institute (now called SRI International). Some of the most notable results of the project include the A search algorithm, the Hough transform, and the visibility graph method. == History == Shakey was developed from approximately 1966 through 1972 with Charles Rosen, Nils Nilsson and Peter Hart as project managers. Other major contributors included Alfred Brain, Sven Wahlstrom, Bertram Raphael, Richard Duda, Richard Fikes, Thomas Garvey, Helen Chan Wolf and Michael Wilber. The project was funded by the Defense Advanced Research Projects Agency (DARPA) based on a SRI proposal submitted in April 1964 for research in "Intelligent Automata", later "Intelligent Automata to Reconnaissance". It was originally designed to have two retractable arms. Now retired from active duty, Shakey is currently on view in a glass display case at the Computer History Museum in Mountain View, California. The project inspired numerous other robotics projects, most notably the Centibots. == Software == The robot's programming was primarily done in LISP. The Stanford Research Institute Problem Solver (STRIPS) planner it used was conceived as the main planning component for the software it utilized. As the first robot that was a logical, goal-based agent, Shakey experienced a limited world. A version of Shakey's world could contain a number of rooms connected by corridors, with doors and light switches available for the robot to interact with. Shakey had a short list of available actions within its planner. These actions involved traveling from one location to another, turning the light switches on and off, opening and closing the doors, climbing up and down from rigid objects, and pushing movable objects around. The STRIPS automated planner could devise a plan to enact all the available actions, even though Shakey himself did not have the capability to execute all the actions within the plan personally. An example mission for Shakey might be something like, an operator types the command "push the block off the platform" at a computer console. Shakey looks around, identifies a platform with a block on it, and locates a ramp in order to reach the platform. Shakey then pushes the ramp over to the platform, rolls up the ramp onto the platform, and pushes the block off the platform. == Hardware == Physically, the robot was particularly tall, and had an antenna for a radio link, sonar range finders, a television camera, on-board processors, and collision detection sensors ("bump detectors"). The robot's tall stature and tendency to shake resulted in its name: We worked for a month trying to find a good name for it, ranging from Greek names to whatnot, and then one of us said, 'Hey, it shakes like hell and moves around, let’s just call it Shakey.' == Research results == The development of Shakey provided far-reaching impact on the fields of robotics and artificial intelligence, as well as computer science in general. Some of the more notable results include the development of the A search algorithm, which is widely used in pathfinding and graph traversal, the process of plotting an efficiently traversable path between points; the Hough transform, which is a feature extraction technique used in image analysis, computer vision, and digital image processing; and the visibility graph method for finding Euclidean shortest paths among obstacles in the plane. == Media and awards == In 1969 the SRI published "SHAKEY: Experimentation in Robot Learning and Planning", a 24-minute video. The project then received media attention. This included an article in the New York Times on April 10, 1969. In 1970, Life referred to Shakey as the "first electronic person"; and in November 1970 National Geographic Magazine covered Shakey and the future of computers. The Association for the Advancement of Artificial Intelligence's AI Video Competition's awards are named "Shakeys" because of the significant impact of the 1969 video. Shakey was inducted into Carnegie Mellon University's Robot Hall of Fame in 2004 alongside such notables as ASIMO and C-3PO. Shakey has been honored with an IEEE Milestone in Electrical Engineering and Computing. Shakey was showcased in the BBC's Towards Tomorrow: Robot (1967) documentary.
Read more →
Andrew Ng

Andrew Yan-Tak Ng (Chinese: 吳恩達; born April 18, 1976) is a British-American computer scientist and technology entrepreneur focusing on machine learning and artificial intelligence (AI). Ng was a cofounder and head of Google Brain and was the former Chief Scientist at Baidu. Ng is an adjunct professor at Stanford University (formerly associate professor and Director of its Stanford AI Lab or SAIL). Ng has also worked in online education, cofounding Coursera and DeepLearning.AI. He has spearheaded many efforts to "democratize deep learning" teaching over 8 million students through his online courses. Ng is renowned globally in computer science, recognized in Time magazine's 100 Most Influential People in 2012 and Fast Company's Most Creative People in 2014. His influence extends to being named in the Time100 AI Most Influential People in 2023. In 2018, he launched and currently heads the AI Fund, initially a $175-million investment fund for backing artificial intelligence startups. He has founded Landing AI, which provides AI-powered SaaS products. On April 11, 2024, Amazon announced Ng's appointment to its board of directors. == Early life and education == Andrew Yan-Tak Ng was born in London, in 1976 to Ronald Paul Ng, a hematologist and lecturer at UCL Medical School, and Tisa Ho, an arts administrator working at the London Film Festival. His parents were both immigrants from Hong Kong. His family moved back to Hong Kong and he spent his early childhood there. In 1984 he and his family moved to Singapore. Ng attended and graduated from Raffles Institution. In 1997, he earned his undergraduate degree with a triple major in computer science, statistics, and economics from Carnegie Mellon University in Pittsburgh, Pennsylvania. Between 1996 and 1998 he also conducted research on reinforcement learning, model selection, and feature selection at the AT&T Bell Labs. In 1998, Ng earned his master's degree in Electrical Engineering and Computer Science from the Massachusetts Institute of Technology (MIT) in Cambridge, Massachusetts. At MIT, he built the first publicly available, automatically indexed web-search engine for research papers on the web. It was a precursor to CiteSeerX/ResearchIndex, but specialized in machine learning. In 2002, he received his Doctor of Philosophy (Ph.D.) in Computer Science from the University of California, Berkeley, under the supervision of Michael I. Jordan. His thesis is titled "Shaping and policy search in reinforcement learning" and is well-cited to this day. == Career == === Academia and teaching === Ng started working as an assistant professor at Stanford University in 2002 and as an associate professor in 2009. Ng is a professor at Stanford University departments of Computer Science and electrical engineering. He served as the director of the Stanford Artificial Intelligence Laboratory (SAIL), where he taught students and undertook research related to data mining, big data, and machine learning. His machine learning course CS229 at Stanford is the most popular course offered on campus with over 1,000 students enrolling some years. As of 2020, three of the most popular courses on Coursera are Ng's: Machine Learning (#1), AI for Everyone (#5), Neural Networks and Deep Learning (#6). In 2008, his group at Stanford was one of the first in the US to start advocating the use of GPUs in deep learning. The rationale was that an efficient computation infrastructure could speed up statistical model training by orders of magnitude, ameliorating some of the scaling issues associated with big data. At the time it was a controversial and risky decision, but since then and following Ng's lead, GPUs have become a cornerstone in the field. Since 2017, Ng has been advocating the shift to high-performance computing (HPC) for scaling up deep learning and accelerating progress in the field. In 2012, along with Stanford computer scientist Daphne Koller he cofounded and was CEO of Coursera, a website that offers free online courses to everyone. It took off with over 100,000 students registered for Ng's popular CS229A course. Today, several million people have enrolled in Coursera courses, making the site one of the leading massive open online courses (MOOCs) in the world. === Industry === From 2011 to 2012, he worked at Google, where he founded and directed the Google Brain Deep Learning Project with Jeff Dean, Greg Corrado, and Rajat Monga. In 2014, he joined Baidu as chief scientist, and carried out research related to big data and AI. There he set up several research teams for things like facial recognition and Melody, an AI chatbot for healthcare. He also developed for the company the AI platform called DuerOS and other technologies that positioned Baidu ahead of Google in the discourse and development of AI. In March 2017, he announced his resignation from Baidu. He soon afterward launched DeepLearning.AI, an online series of deep learning courses (including the AI for Good Specialization). Then Ng launched LandingAI, which provides AI-powered SaaS products. In January 2018, Ng unveiled the AI Fund, raising $175 million to invest in new startups. In November 2021, LandingAI secured a $57 million round of series A funding led by McRock Capital, to help enterprises adopt AI. In October 2024, Ng's AI Fund made its first investment in India, backing AI healthcare startup Jivi, which uses AI for diagnoses, treatment recommendations, and administrative tasks. The investment highlights the growth of India's AI sector, expected to reach $22 billion by 2027. === Research === Ng researches primarily in machine learning, deep learning, machine perception, computer vision, and natural language processing; and is one of the world's most famous and influential computer scientists. He's frequently won best paper awards at academic conferences and has had a huge impact on the field of AI, computer vision, and robotics. During graduate school, together with David M. Blei and Michael I. Jordan, Ng co-authored the influential paper that introduced latent Dirichlet allocation (LDA) for his thesis on reinforcement learning for drones. His early work includes the Stanford Autonomous Helicopter project, which developed one of the most capable autonomous helicopters in the world. He was the leading scientist and principal investigator on the STAIR (Stanford Artificial Intelligence Robot) project, which resulted in Robot Operating System (ROS), a widely used open source software robotics platform. His vision to build an AI robot and put a robot in every home inspired Scott Hassan to back him and create Willow Garage. He is also one of the founding team members for the Stanford WordNet project, which uses machine learning to expand the Princeton WordNet database created by Christiane Fellbaum. In 2011, Ng founded the Google Brain project at Google, which developed large-scale artificial neural networks using Google's distributed computing infrastructure. Among its notable results was a neural network trained using deep learning algorithms on 16,000 CPU cores, which learned to recognize cats after watching only YouTube videos, and without ever having been told what a "cat" is. The project's technology is also currently used in the Android operating system's speech recognition system. === Views on AI === Ng thinks that the real threat is contemplating the future of work: "Rather than being distracted by evil killer robots, the challenge to labor caused by these machines is a conversation that academia and industry and government should have." He has emphasized the importance of expanding access to AI education, stating that empowering people around the world to use AI tools is essential to building AI applications. In a December 2023 Financial Times interview, Ng highlighted concerns regarding the impact of potential regulations on open-source AI, emphasizing how reporting, licensing, and liability risks could unfairly burden smaller firms and stifle innovation. He argued that regulating basic technologies like open-source models could hinder progress without markedly enhancing safety. Ng advocated for carefully designed regulations to prevent obstacles to the development and distribution of beneficial AI technologies. In a June 2024 interview with the Financial Times, Ng expressed concerns about proposed AI legislation in California that would have required developers to implement safety mechanisms such as a "kill switch" for advanced models. He described the bill as creating "massive liabilities for science-fiction risks" and said it "stokes fear in anyone daring to innovate." Other critics argued the bill would impose burdens on open-source developers and smaller AI companies. The bill was ultimately vetoed by Governor Gavin Newsom in September 2024. == Online education: massive open online course == In 2011, Stanford launched a total of three massive open online course (MOOCs) on machine learning (CS229a), databases, and AI, taught by Ng
Read more →
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 →
Rejoyn

Rejoyn is a prescription-only digital therapeutic smartphone app approved by the US FDA for the treatment of major depressive disorder (MDD) in adults ages 22 and up. It is prescribed in conjunction with standard antidepressant medication and professional guidance and support. Rejoyn was developed by Click Therapeutics and Otsuka America Pharmaceutical Inc., and gained FDA clearance as a "medical device" on March 30th, 2024. The smartphone app helps patients with depression using exercises based on cognitive behavioral therapy (CBT) along with timed notifications to keep the patient engaged and in treatment. Randomized controlled trials showed that the Rejoyn app was more effective at relieving depression symptoms compared to a "sham app", a placebo app that required similar effort but was not intended to be helpful. Dr. John Torous, MD, MBI,[a] a psychiatrist at the Beth Israel Deaconess Medical Center in Boston, said that the app seems to pose minimal risks, and is an important step forward in unlocking the power of smartphones in treating psychiatric disorders. Some experts have signaled that the claims should be taken with caution, since the app was "tested only in a narrow subset of patients." and its benefits are "not statistically significant," according to the study’s primary outcome."
Read more →
Leading the Future

Leading the Future is an American super PAC network focused on lobbying for policies friendly to the artificial intelligence industry. It was launched in 2025 with over $100 million from industry stakeholders including Andreessen Horowitz, OpenAI President Greg Brockman and Palantir co-founder Joe Lonsdale. The launch was preceded by talks between Collin McCune, head of government affairs at Andreessen Horowitz, and Chris Lehane, chief global affairs officer at OpenAI. Among the members of the network are the American Mission PAC, which supported Chris Gober, and the Think Big PAC, which targeted Alex Bores. Leading the Future is affiliated with the nonprofit Build American AI, which Axios describes as a dark money advocacy "offshoot" operating alongside the super PAC. NBC News states that the network’s efforts are modeled after the pro-cryptocurrency group Fairshake. Leading the Future is led by Zac Moffatt and Josh Vlasto, the latter of whom previously served as an advisor to Fairshake. In response to the creation of Leading the Future, former members of Congress Brad Carson and Chris Stewart co-founded the super PAC network Public First, aiming to counter the group’s influence. In April 2026, an investigation by Model Republic linked Leading the Future to The Wire By Acutus, an automated news website that allegedly used AI agents posing as human journalists to solicit interviews. The site's content was found to closely mirror the PAC's deregulatory policy goals while targeting researchers and advocates skeptical of rapid AI development. In May 2026, Wired revealed that Build American AI used a "dark money" campaign to pay TikTok and Instagram influencers $5,000 per video to promote scripted narratives framing Chinese AI as a "national security threat." According to internal documents and staff at the marketing agency managing the project, the campaign's explicit goal was to "subtly shift public debate" toward the deregulation of AI industries while intentionally avoiding technical discussions regarding AI quality or safety. During the 2026 primary season Leading the Future went on to endorse several candidates in both Democratic and Republican races with several of them going on to win.
Read more →
Rnn (software)

rnn is an open-source machine learning framework that implements recurrent neural network architectures, such as LSTM and GRU, natively in the R programming language, that has been downloaded over 100,000 times (from the RStudio servers alone). The rnn package is distributed through the Comprehensive R Archive Network under the open-source GPL v3 license. == Workflow == The below example from the rnn documentation show how to train a recurrent neural network to solve the problem of bit-by-bit binary addition. == sigmoid == The sigmoid functions and derivatives used in the package were originally included in the package, from version 0.8.0 onwards, these were released in a separate R package sigmoid, with the intention to enable more general use. The sigmoid package is a dependency of the rnn package and therefore automatically installed with it. == Reception == With the release of version 0.3.0 in April 2016 the use in production and research environments became more widespread. The package was reviewed several months later on the R blog The Beginner Programmer as "R provides a simple and very user friendly package named rnn for working with recurrent neural networks.", which further increased usage. The book Neural Networks in R by Balaji Venkateswaran and Giuseppe Ciaburro uses rnn to demonstrate recurrent neural networks to R users. It is also used in the r-exercises.com course "Neural network exercises". The RStudio CRAN mirror download logs show that the package is downloaded on average about 2,000 per month from those servers , with a total of over 100,000 downloads since the first release, according to RDocumentation.org, this puts the package in the 15th percentile of most popular R packages .
Read more →
Script theory

Script theory is a psychological theory which posits that human behaviour largely falls into patterns called scripts because they function the way a written script does, by providing a program for action. Silvan Tomkins created script theory as a further development of his affect theory, which regards human beings' emotional responses to stimuli as falling into categories called affects: he noticed that the purely biological response of affect may be followed by awareness and by what we cognitively do in terms of acting on that affect, so that more was needed to produce a complete explanation of what he called human being theory. These scripts fall under the larger cognitive concept called schemas, which are organized chunks of information. A schema is a script that has the potential to lack the specificity of the sequence of events. A schema becomes a script is when there is an ordering to it that requires action, such as the process of starting a car (get in, put on the seatbelt, turn the car on, release the emergency brake, etc.). In script theory, the basic unit of analysis is called a scene, defined as a sequence of events linked by the affects triggered during the experience of those events. Tomkins recognized that affective experiences fall into patterns that we may group together according to criteria, such as the types of persons and places involved and the degree of intensity of the effect experienced—the patterns of which constitute scripts that inform behavior in an effort to maximize positive affect and to minimize negative affect. == In artificial intelligence == Roger Schank, Robert P. Abelson and their research group extended Tomkins' scripts and used them in early artificial intelligence work as a method of representing procedural knowledge. In their work, scripts are very much like frames, except the values that fill the slots must be ordered. A script is a structured representation describing a stereotyped sequence of events in a particular context. Scripts are used in natural-language understanding systems to organize a knowledge base in terms of the situations that the system should understand. The classic example of a script involves the typical sequence of events that occur when a person drinks in a restaurant: finding a seat, reading the menu, ordering drinks from the waitstaff, etc. In the script form, these would be decomposed into conceptual transitions, such as MTRANS and PTRANS, which refer to mental transitions [of information] and physical transitions [of things]. Schank, Abelson and their colleagues tackled some of the most difficult problems in artificial intelligence (i.e., story understanding), but ultimately their line of work ended without tangible success. This type of work received little attention after the 1980s, but became very influential in later knowledge representation techniques, such as case-based reasoning. Scripts can be inflexible. To deal with inflexibility, smaller modules called memory organization packets (MOP) can be combined in a way that is appropriate for the situation.
Read more →
WaveMaker

WaveMaker is a Java-based low-code development platform designed for building software applications and platforms. The company, WaveMaker Inc., is based in Mountain View, California. The platform is intended to assist enterprises in speeding up their application development and IT modernization initiatives through low-code capabilities. Additionally, for independent software vendors (ISVs), WaveMaker serves as a customizable low-code component that integrates into their products. The WaveMaker Platform is a licensed software platform allowing organizations to establish their own end-to-application platform-as-a-service (PaaS) for the creation and operation of custom apps. It allows developers and business users to create apps that are customizable. These applications can seamlessly consume APIs, visualize data, and automatically adapt to multi-device responsive interfaces. WaveMaker's low-code platform allows organizations to deploy applications on either public or private cloud infrastructure. Containers can be deployed on top of virtual machines or directly on bare metal. The software features a graphical user interface (GUI) console for managing IT app infrastructure, leveraging the capabilities of Docker containerization. The solution offers functionalities for automating application deployment, managing the application lifecycle, overseeing release management, and controlling deployment workflows and access permissions: Apps for web, tablet, and smartphone interfaces Enterprise technologies like Java, Hibernate, Spring, AngularJS, JQuery Docker-provided APIs and CLI Software stack packaging, container provisioning, stack and app upgrading, replication, and fault tolerance == WaveMaker Studio == WaveMaker RAD Platform is built around WaveMaker Studio, a WYSIWYG rapid development tool that allows business users to compose an application using a drag-and-drop method. WaveMaker Studio supports rapid application development (RAD) for the web, similar to what products like PowerBuilder and Lotus Notes provided for client-server computing. WaveMaker Studio allows developers to produce an application once, then automatically adjust it for a particular target platform, whether a PC, mobile phone, or tablet. Applications created using the WaveMaker Studio follow a model–view–controller architecture. WaveMaker Studio has been downloaded more than two million times. The Studio community consists of 30,000 registered users. Applications generated by WaveMaker Studio are licensed under the Apache license. Studio 8 was released on September 25, 2015. The prior version, Studio 7, has some notable development milestones. It was based on AngularJS framework, previous Studio versions (6.7, 6.6, 6.5) use the Dojo Toolkit. Some of the features WaveMaker Studio 7 include: Automatic generation of Hibernate mapping, and Hibernate queries from database schema import. Automatic creation of Enterprise Data Widgets based on schema import. Each widget can display data from a database table as a grid or edit form. Edit form implements create, update, and delete functions automatically. WYSIWYG Ajax development studio runs in a browser. Deployment to Tomcat, IBM WebSphere, Weblogic, JBoss. Mashup tool to assemble web applications based on SOAP, REST and RSS web services, Java Services and databases. Supports existing CSS, HTML and Java code. The ability to deploy a standard Java .war file. == Technologies and frameworks == WaveMaker allows users to build applications that run on "Open Systems Stack" based on the following technologies and frameworks: AngularJS, Bootstrap, NVD3, HTML, CSS, Apache Cordova, Hibernate, Spring, Spring Security, Java. The various supported integrations include: Databases: Oracle, MySQL, Microsoft SQL Server, PostgreSQL, IBM DB2, HSQLDB Authentication: LDAP, Active Directory, CAS, Custom Java Service, Database Version Control: Bitbucket (or Stash), GitHub, Apache Subversion Deployment: Amazon AWS, Microsoft Azure, WaveMaker Private Cloud (Docker containerization), IBM Web Sphere, Apache Tomcat, SpringSource tcServer, Oracle WebLogic Server, JBoss(WildFly), GlassFish App Stores: Google Play, Apple App Store, Windows Store == History == In 2003, WaveMaker was founded as ActiveGrid. Then, in 2007, it was rebranded as Wavemaker. It was acquired by VMware in 2011. In March 2013, support for the WaveMaker project was discontinued. In May 2013, Pramati Technologies acquired the assets of WaveMaker. In February 2014, Wavemaker Studio 6.7 was released, which was the last open source version of Studio. In September 2014 WaveMaker Inc. launched the WaveMaker RAD Platform, which allowed organizations to run their own application platform for building and running apps. In March 2023, WaveMaker released version 11.5, which includes enhanced low-code development capabilities and new AI-driven tools to streamline the application development process.
Read more →
BabelNet

BabelNet is a multilingual lexical-semantic knowledge graph, ontology and encyclopedic dictionary developed at the NLP group of the Sapienza University of Rome under the supervision of Roberto Navigli. BabelNet was automatically created by linking Wikipedia to the most popular computational lexicon of the English language, WordNet. The integration is done using an automatic mapping and by filling in lexical gaps in resource-poor languages by using statistical machine translation. The result is an encyclopedic dictionary that provides concepts and named entities lexicalized in many languages and connected with large amounts of semantic relations. Additional lexicalizations and definitions are added by linking to free-license wordnets, OmegaWiki, the English Wiktionary, Wikidata, FrameNet, VerbNet and others. Similarly to WordNet, BabelNet groups words in different languages into sets of synonyms, called Babel synsets. For each Babel synset, BabelNet provides short definitions (called glosses) in many languages harvested from both WordNet and Wikipedia. == Statistics of BabelNet == As of December 2023, BabelNet (version 5.3) covers 600 languages. It contains almost 23 million synsets and around 1.7 billion word senses (regardless of their language). Each Babel synset contains 2 synonyms per language, i.e., word senses, on average. The semantic network includes all the lexico-semantic relations from WordNet (hypernymy and hyponymy, meronymy and holonymy, antonymy and synonymy, etc., totaling around 364,000 relation edges) as well as an underspecified relatedness relation from Wikipedia (totaling around 1.9 billion edges). Version 5.3 also associates around 61 million images with Babel synsets and provides a Lemon RDF encoding of the resource, available via a SPARQL endpoint. 2.67 million synsets are assigned domain labels. == Applications == BabelNet has been shown to enable multilingual natural language processing applications. The lexicalized knowledge available in BabelNet has been shown to obtain state-of-the-art results in: Semantic relatedness, Multilingual word-sense disambiguation and entity linking, with the Babelfy system, Video games with a purpose. == Prizes and acknowledgments == BabelNet received the META prize 2015 for "groundbreaking work in overcoming language barriers through a multilingual lexicalised semantic network and ontology making use of heterogeneous data sources". The Artificial Intelligence Journal paper that describes BabelNet won the Prominent Paper Award in 2017. BabelNet featured prominently in a Time magazine article about the new age of innovative and up-to-date lexical knowledge resources available on the Web.
Read more →
Mira Murati

Ermira "Mira" Murati (born 16 December 1988) is an Albanian-American business executive. She launched an AI startup called Thinking Machines Lab in February 2025. Previously she was the chief technology officer of OpenAI, and a senior product manager at Tesla. == Early life and education == Murati was born on 16 December 1988 in Vlorë, Albania. She is fluent in Italian. At age 16, she won a United World Colleges (UWC) scholarship to study at Pearson College on Vancouver Island in Canada, from which she graduated in 2007 with an International Baccalaureate. After Pearson, she went to the United States to pursue further studies through a dual-degree program, earning a Bachelor of Arts from Colby College in 2011, and a Bachelor of Engineering degree from Dartmouth College's Thayer School of Engineering in 2012. == Career == === Early career === Murati interned in 2011 as a summer analyst at Goldman Sachs in Tokyo, Japan. She then briefly worked for Zodiac Aerospace as an intern before joining the electric car company Tesla in 2013 as a product manager on the Model X. From 2016 to 2018, she worked for the augmented reality start-up Leap Motion (now Ultraleap). === OpenAI === In 2018, she joined OpenAI as the VP of Applied AI and partnerships. She became chief technology officer (CTO) in May 2022. She led OpenAI's work on ChatGPT, Dall-E, Codex and Sora, while overseeing its research, product and safety teams. She oversaw technical advancements and direction of OpenAI's various projects, including the development of advanced AI models and tools. Murati worked on several of OpenAI's notable products, such as the Generative Pretrained Transformer (GPT) series of language models. Commenting about the potential loss of creative jobs to AI, Murati said that "maybe [the jobs] shouldn’t have been there in the first place". In October 2023, Murati was ranked 57th on Fortune's list of "The 100 Most Powerful Women in Business of 2023". In November 2023, Murati became interim chief executive officer of OpenAI following the removal of Sam Altman from the job. She had collaborated with Ilya Sutskever, whose 52-page memo outlining concerns about Altman relied heavily on screenshots and information she provided, which contributed to the board's decision to oust him. Murati was replaced by Emmett Shear three days later, who left when Altman was reinstated five days later. Following these events, Murati returned to her role as CTO. In June 2024, Dartmouth College awarded Murati an honorary Doctor of Science for having "democratized technology and advanced a better, safer world for us all". In September 2024, Murati announced that she was stepping down as CTO to allow her the opportunity to "do my own exploration". This move came amid a wider executive exodus as OpenAI chief research officer Bob McGrew and a vice president of research, Barret Zoph, also announced their departures soon after. === Thinking Machines Lab === In February 2025, Murati launched Thinking Machines Lab, a new public benefit corporation aiming "to make AI systems more widely understood, customizable, and generally capable". She was reported to have hired "a team of about 30 leading researchers and engineers from competitors including Meta, Mistral, and OpenAI." People involved with the startup include OpenAI cofounder John Schulman, and advisors Alec Radford and Bob McGrew. The following month, Bloomberg reported that the company had reached an estimated valuation of $9 billion, with an "average founder stake value" of $1.4 billion. In April 2025, Thinking Machines Lab reportedly aimed for a $2 billion seed round (requiring a minimum investment of $50 million). The round was led by Andreessen Horowitz and included participation from the government of Albania, valuing the company at $12 billion. Thinking Machines Lab follows a governance structure wherein Mira Murati holds a deciding vote on board matters, weighted to provide her with a majority decision-making capability. In October 2025, Thinking Machines Lab announced its first product, Tinker, a tool used to create custom frontier AI models. == Publications == Murati, Ermira (Spring 2022). "Language & Coding Creativity". Daedalus. 151 (2). Cambridge, MA: American Academy of Arts and Sciences (AAAS): 156–167. doi:10.1162/daed_a_01907. Retrieved 25 September 2024.
Read more →
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 →
Apache Drill

Apache Drill is an open-source software framework that supports data-intensive distributed applications for interactive analysis of large-scale datasets. Built chiefly by contributions from developers from MapR, Drill is inspired by Google's Dremel system. Drill is an Apache top-level project. Drill supports a variety of NoSQL databases and file systems, including Alluxio, HBase, MongoDB, MapR-DB, HDFS, MapR-FS, Amazon S3, Azure Blob Storage, Google Cloud Storage, Swift, NAS and local files. A single query can join data from multiple datastores. Drill's datastore-aware optimizer automatically restructures a query plan to leverage the datastore's internal processing capabilities. In addition, Drill supports data locality, if Drill and the datastore are on the same nodes. Tom Shiran is the founder of the Apache Drill Project. It was designated an Apache Software Foundation top-level project in December 2016. == Features == One explicitly stated design goal is that Drill is able to scale to 10,000 servers or more and to be able to process petabytes of data and trillions of records in seconds. Schema-free JSON document model similar to MongoDB and Elasticsearch, without requiring a formal schema to be declared Industry-standard APIs: ANSI SQL, ODBC/JDBC, RESTful APIs Extremely user and developer friendly Pluggable architecture enables connectivity to multiple datastores Version 1.9 added dynamic user-defined functions Version 1.11 added cryptographic-related functions and PCAP file format support == Back-end support == Drill is primarily focused on non-relational datastores, including Apache Hadoop text files, NoSQL, and cloud storage. A notable feature also includes in situ querying of local JSON and Apache Parquet files. Some additional datastores that it supports include: All Hadoop distributions (HDFS API 2.3+), including Apache Hadoop, MapR, CDH and Amazon EMR NoSQL: MongoDB, Apache HBase, Apache Cassandra Online Analytical Processing: Apache Kudu, Apache Druid, OpenTSDB Cloud storage: Amazon S3, Google Cloud Storage, Azure Blob Storage, Swift, IBM Cloud Object Storage Diverse data formats, including Apache Avro, Apache Parquet and JSON RDBMs storage plugins (Using JDBC to connect to MySQL, PostgreSQL, and others) A new datastore can be added by developing a storage plugin. Drill's "schema-free" JSON data model enables it to query non-relational datastores in-situ . == Front-end support == Drill itself can be queried via JDBC, ODBC, or REST through a variety of methods and languages including Python and Java. The default install includes a web interface allowing end-users to execute ANSI SQL directly and export data tables as CSV files without any programming. The dashboard library, Apache Superset, is particularly well suited for visualization of data queried with Drill.
Read more →
Aidan Gomez

Aidan Gomez is a British-Canadian computer scientist working in the field of artificial intelligence, with a focus on natural language processing. He is the co-founder and CEO of the technology company Cohere. == Early life and education == Gomez grew up in Brighton, Ontario. He graduated from the University of Toronto with a bachelor's degree in computer science and mathematics. He was pursuing a PhD in computer science from the University of Oxford. He paused his studies to launch Cohere. He was granted the PhD in 2024. == Career == In 2017, as a 20 year-old intern at Google Brain, Gomez was one of eight authors of the research paper "Attention Is All You Need", which is credited with changing the AI industry and helping lead to the creation of ChatGPT. The paper proposed a novel deep learning architecture called the transformer, that enables machine learning models to analyze large amounts of data for patterns, and then use those patterns to make predictions while leveraging GPU parallelization. It has been commonly adopted for training large language models and in the development of generative AI. In the same year, Gomez founded FOR.ai, a program to help researchers learn machine learning techniques in a collaborative format. An outgrowth of this project was Cohere For AI (now Cohere Labs), which released Aya, an open-source multilingual LLM. As a PhD student, Gomez worked as a machine learning researcher at Google Brain. At that time, he co-authored the paper "One Model to Learn Them All" about multi-task learning by a single neural network. In 2019, Gomez left Google Brain to launch Cohere, an enterprise-focused company that helps businesses implement AI into chatbots, search engines, and other products. As of Sept 2025, Cohere has raised about US$1.6 billion at valuation north of $7 billion, as Gomez leads the company as its CEO. Gomez was named to the 2023 Time 100/AI list of the most influential people in the field of artificial intelligence. He and his fellow Cohere founders Ivan Zhang and Nick Frosst were named number 1 on 2023 Maclean's AI Trailblazers Power List. In April 2025, Gomez was elected to the board of Rivian. == Views on AI == Gomez has stated that warnings regarding the existential risk from artificial intelligence are overblown, and that real risks involve the automated spread of misinformation on social media. He said that the United States would win the AI arms race over China.
Read more →
Computer Power and Human Reason

Computer Power and Human Reason: From Judgment to Calculation is a 1976 nonfiction book by German-American computer scientist Joseph Weizenbaum in which he contends that while artificial intelligence may be possible, we should never allow computers to make important decisions, as they will always lack human qualities such as compassion and wisdom. == Background == Before writing Computer Power and Human Reason, Weizenbaum had garnered significant attention for creating the ELIZA program, an early milestone in conversational computing. His firsthand observation of people attributing human-like qualities to a simple program prompted him to reflect more deeply on society's readiness to entrust moral and ethical considerations to machines. == Reception and legacy == Computer Power and Human Reason sparked scholarly debate on the acceptable scope of AI applications, particularly in fields where human welfare and ethical considerations are paramount. Early academic reviews highlighted that Weizenbaum's stance pushed readers to recognize that even as computers grow more capable, they lack the intrinsic moral compass and empathy required for certain kinds of judgment. The book caused disagreement with, and separation from, other members of the artificial intelligence research community, a status the author later said he'd come to take pride in.
Read more →