NETtalk is an artificial neural network that learns to pronounce written English text by supervised learning. It takes English text as input, and produces a matching phonetic transcriptions as output. It is the result of research carried out in the mid-1980s by Terrence Sejnowski and Charles Rosenberg. The intent behind NETtalk was to construct simplified models that might shed light on the complexity of learning human level cognitive tasks, and their implementation as a connectionist model that could also learn to perform a comparable task. The authors trained it by backpropagation. The network was trained on a large amount of English words and their corresponding pronunciations, and is able to generate pronunciations for unseen words with a high level of accuracy. The output of the network was a stream of phonemes, which fed into DECtalk to produce audible speech. It achieved popular success, appearing on the Today show. From the point of view of modeling human cognition, NETtalk does not specifically model the image processing stages and letter recognition of the visual cortex. Rather, it assumes that the letters have been pre-classified and recognized. It is NETtalk's task to learn proper associations between the correct pronunciation with a given sequence of letters based on the context in which the letters appear. A similar architecture was subsequently used for the opposite task, that of converting continuous speech signal to a phoneme sequence. == Training == The training dataset was a 20,008-word subset of the Brown Corpus, with manually annotated phoneme and stress for each letter. The development process was described in a 1993 interview. It took three months -- 250 person-hours -- to create the training dataset, but only a few days to train the network. After it was run successfully on this, the authors tried it on a phonological transcription of an interview with a young Latino boy from a barrio in Los Angeles. This resulted in a network that reproduced his Spanish accent. The original NETtalk was implemented on a Ridge 32, which took 0.275 seconds per learning step (one forward and one backward pass). Training NETtalk became a benchmark to test for the efficiency of backpropagation programs. For example, an implementation on Connection Machine-1 (with 16384 processors) ran at 52x speedup. An implementation on a 10-cell Warp ran at 340x speedup. The following table compiles the benchmark scores as of 1988. Speed is measured in "millions of connections per second" (MCPS). For example, the original NETtalk on Ridge 32 took 0.275 seconds per forward-backward pass, giving 18629 / 10 6 0.275 = 0.068 {\displaystyle {\frac {18629/10^{6}}{0.275}}=0.068} MCPS. Relative times are normalized to the MicroVax. == Architecture == The network had three layers and 18,629 adjustable weights, large by the standards of 1986. There were worries that it would overfit the dataset, but it was trained successfully. The input of the network has 203 units, divided into 7 groups of 29 units each. Each group is a one-hot encoding of one character. There are 29 possible characters: 26 letters, comma, period, and word boundary (whitespace). To produce the pronunciation of a single character, the network takes the character itself, as well as 3 characters before and 3 characters after it. The hidden layer has 80 units. The output has 26 units. 21 units encode for articulatory features (point of articulation, voicing, vowel height, etc.) of phonemes, and 5 units encode for stress and syllable boundaries. Sejnowski studied the learned representation in the network, and found that phonemes that sound similar are clustered together in representation space. The output of the network degrades, but remains understandable, when some hidden neurons are removed.
Hallucination (artificial intelligence)
In the field of artificial intelligence (AI), a hallucination or artificial hallucination (also called bullshitting, confabulation, or delusion) is a response generated by AI that contains false or misleading information presented as fact. This term draws a loose analogy with human psychology, where a hallucination typically involves false percepts. For example, a chatbot powered by large language models (LLMs), like ChatGPT, may embed plausible-sounding random falsehoods within its generated content. Detecting and mitigating errors and hallucinations pose significant challenges for practical deployment and reliability of LLMs in high-stakes scenarios, such as chip design, supply chain logistics, and medical diagnostics. Some software engineers and statisticians have criticized the specific term "AI hallucination" for unreasonably anthropomorphizing computers. Symbolic artificial intelligence models generally do not produce hallucinations, unlike large language models. == Term == === Origin === Since the 1980s, the term "hallucination" has been used in computer vision with a positive connotation to describe the process of adding detail to an image. For example, the task of generating high-resolution face images from low-resolution inputs is called face hallucination. The first documented use of the term "hallucination" in this sense is in the PhD thesis of Eric Mjolsness in 1986. A notable work is the face hallucination algorithm by Simon Baker and Takeo Kanade published in 1999. In the 2000s, hallucinations were described in statistical machine translation as a failure mode. Since the 2010s, the term has undergone a semantic shift to signify the generation of factually incorrect or misleading outputs by AI systems in tasks like machine translation and object detection. In 2015, hallucinations were identified in visual semantic role labeling tasks by Saurabh Gupta and Jitendra Malik. In 2015, computer scientist Andrej Karpathy used the term "hallucinated" in a blog post to describe his recurrent neural network (RNN) language model generating an incorrect citation link. In 2017, Google researchers used the term to describe the responses generated by neural machine translation (NMT) models when they are not related to the source text, and in 2018, the term was used in computer vision to describe instances where non-existent objects are erroneously detected because of adversarial attacks. In July 2021, Meta warned during its release of BlenderBot 2 that the system is prone to "hallucinations", which Meta defined as "confident statements that are not true". Following OpenAI's ChatGPT release in beta version in November 2022, some users complained that such chatbots often seem to pointlessly embed plausible-sounding random falsehoods within their generated content. Many news outlets, including The New York Times, started to use the term "hallucinations" to describe these models' frequently incorrect or inconsistent responses. In 2023, the Cambridge dictionary updated its definition of hallucination to include this new sense specific to the field of AI. Some researchers have highlighted a lack of consistency in how the term is used, but also identified several alternative terms in the literature, such as confabulations, fabrications, and factual errors. === Definitions and alternatives === Uses, definitions and characterizations of the term "hallucination" in the context of LLMs include: "a tendency to invent facts in moments of uncertainty" (OpenAI, May 2023) "a model's logical mistakes" (OpenAI, May 2023) "fabricating information entirely, but behaving as if spouting facts" (CNBC, May 2023) "making up information" (The Verge, February 2023) "probability distributions" (in scientific contexts) Journalist Benj Edwards, in Ars Technica, writes that the term "hallucination" is controversial, but that some form of metaphor remains necessary; Edwards suggests "confabulation" as an analogy for processes that involve "creative gap-filling". In July 2024, a White House report on fostering public trust in AI research mentioned hallucinations only in the context of reducing them. Notably, when acknowledging David Baker's Nobel Prize-winning work with AI-generated proteins, the Nobel committee avoided the term entirely, instead referring to "imaginative protein creation". Hicks, Humphries, and Slater, in their article in Ethics and Information Technology, argue that the output of LLMs is "bullshit" under Harry Frankfurt's definition of the term, and that the models are "in an important way indifferent to the truth of their outputs", with true statements only accidentally true, and false ones accidentally false. Some researchers also use the derogatory term "botshit", often referring to uncritical use of AI. === Criticism === In the scientific community, some researchers avoid the term "hallucination", seeing it as potentially misleading. It has been criticized by Usama Fayyad, executive director of the Institute for Experimental Artificial Intelligence at Northeastern University, on the grounds that it misleadingly personifies large language models and is vague. Mary Shaw said, "The current fashion for calling generative AI's errors 'hallucinations' is appalling. It anthropomorphizes the software, and it spins actual errors as somehow being idiosyncratic quirks of the system even when they're objectively incorrect." In Salon, statistician Gary Smith argues that LLMs "do not understand what words mean" and consequently that the term "hallucination" unreasonably anthropomorphizes the machine. Murray Shanahan argues that anthropomorphic framing of LLM capabilities, including terms like "hallucination", encourages users and researchers to attribute cognitive processes to systems that operate through statistical pattern completion, and advocates for more careful linguistic practices when discussing LLM behavior. Kristina Šekrst argues that applying psychological vocabulary to LLM outputs obscures the difference between the appearance of mental properties and their genuine presence. Förster & Skop assert that tech companies use the hallucination metaphor to anthropomorphize models and deflect responsibility for non-factual outputs. Some see the AI outputs not as illusory but as prospective—that is, having some chance of being true, similar to early-stage scientific conjectures. The term has also been criticized for its association with psychedelic drug experiences. == In natural language generation == In natural language generation, there are several reasons why natural language models hallucinate: === Hallucination from data === Hallucinations can stem from incomplete, inaccurate or unrepresentative data sets. === Modeling-related causes === The pre-training of generative pretrained transformers (GPT) involves predicting the next word. It incentivizes GPT models to "give a guess" about what the next word is, even when they lack information. Some researchers take an anthropomorphic perspective and posit that hallucinations arise from a tension between novelty and usefulness. For instance, Amabile and Pratt define human creativity as the production of novel and useful ideas. By extension, a focus on novelty in machine creativity can lead to the production of original but inaccurate responses—that is, falsehoods—whereas a focus on usefulness may result in memorized content lacking originality. By 2022, newspapers such as The New York Times expressed concern that, as the adoption of bots based on large language models continued to grow, unwarranted user confidence in bot output could lead to problems. === Interpretability research === In 2025, interpretability research by Anthropic on the LLM Claude identified internal circuits that cause it to decline to answer questions unless it knows the answer. By default, the circuit is active and the LLM doesn't answer. When the LLM has sufficient information, these circuits are inhibited and the LLM answers the question. Hallucinations were found to occur when this inhibition happens incorrectly, such as when Claude recognizes a name but lacks sufficient information about that person, causing it to generate plausible but untrue responses. === Examples === On 15 November 2022, researchers from Meta AI published Galactica, designed to "store, combine and reason about scientific knowledge". Content generated by Galactica came with the warning: "Outputs may be unreliable! Language Models are prone to hallucinate text." In one case, when asked to draft a paper on creating avatars, Galactica cited a fictitious paper from a real author who works in the relevant area. Meta withdrew Galactica on 17 November due to offensiveness and inaccuracy. OpenAI's ChatGPT, released in beta version to the public on November 30, 2022, was based on the foundation model GPT-3.5 (a revision of GPT-3). Professor Ethan Mollick of Wharton called it an "omniscient, eager-to-please intern who sometimes lies to you". Data scientist Teresa Kuba
Shader lamps
Shader lamps is a computer graphic technique used to change the appearance of physical objects. The still or moving objects are illuminated, using one or more video projectors, by static or animated texture or video stream. The method was invented at University of North Carolina at Chapel Hill by Ramesh Raskar, Greg Welch, Kok-lim Low and Deepak Bandyopadhyay in 1999 [1] as a follow on to Spatial Augmented Reality [2] also invented at University of North Carolina at Chapel Hill in 1998 by Ramesh Raskar, Greg Welch and Henry Fuchs. A 3D graphic rendering software is typically used to compute the deformation caused by the non perpendicular, non-planar or even complex projection surface. Complex objects (or aggregation of multiple simple objects) create self shadows that must be compensated by using several projectors. The objects are typically replaced by neutral color ones, the projection giving all its visual properties, thus the name shader lamps. The technique can be used to create a sense of invisibility, by rendering transparency. The object is illuminated not by a replacement of its own visual properties, but by the corresponding visual surface placed behind the object as seen from an arbitrary viewing point.
RockMyRun
Rock My Run (stylized as RockMyRun; trademarked slogan: "The Best Running Music in the World™") is a mobile running/fitness app founded in 2011 that provides running and workout music in the form of DJ mixes. It is owned by Rock My World, Inc., a health and fitness technology company based in San Diego, California. The app allows users to listen to these professional DJ mixes on their smartphone while running or working out to enhance and motivate their performance. Rock My World, Inc. also developed the app Jolt.ai for the software Slack. == History == During the early stages of the company, Rock My World, Inc. raised more than $2 million in funding generated by the Irvine Company's The Vine SD and from institutional investors including Skullcandy, ZTE and Lighter Capital and were admitted to the Plug and Play Tech Center in Sunnyvale and to the tech incubator EvoNexus in San Diego. In an interview with co-founder and ex-Qualcomm staff Adam Riggs-Zeigen, he said that "from the beginning [their] big goal is to help people live healthier lives." == Features == The RockMyRun app contains thousands of mixes or "stations" produced by its professional DJs intended to increase enjoyment and performance during exercise. DJs who have provided mixes for the app include David Guetta, Zedd, Steve Aoki, Major Lazer and Afrojack. All of the music can be personalized based on the user's steps per minute, heart rate or ideal cadence allowing the user to "always hear the right music at the right time at the right tempo". All RockMyRun mixes are organized into stations to help users discover music that suits their needs. RockMyRun contains mixes of all genres and each station is categorized into their respective genres and displays tags to let users know the type of music contained in the mix. RockMyRun has two membership types; it is free as a standard member, but for uninterrupted listening and additional features, users can upgrade to a paid "Rockstar" membership. Since March 2023, couples can now be on the same RockMyRun playlists and "share" earbuds. This allows people to train together, easier. A group of DJs curate playlists for specific training needs and different energy levels. == Reception == RockMyRun has been featured on television programs such as The Today Show on two occasions and on The Rachael Ray Show, and in positive reviews by many publications and websites including The New York Times on four separate occasions, TIME, The Huffington Post, The Denver Post, Men's Fitness, Real Simple, The Vulcan Post, The L.A. Times, Glamour, Paste magazine, PCMag, Dubai Week, BetaNews, CNET, CNBC, Reuters, Insider, Tom's Guide and Yahoo! Tech. RockMyRun has also been mentioned/recommended in books/publications such as A Practical Guide to Teacher Wellbeing by Elizabeth Holmes and Applying Music in Exercise and Sport by Dr. Costas Karageorghis. Ultimate Ears placed RockMyRun at the top of their list at No. 1 on their "5 Favorite Workout Music Apps". In a positive review by David Strausser for AndroidGuys in 2015, he praised the app in a detailed review, saying "The mixes are incredible and the rates are reasonable. The app is quick, beautiful." In 2015, Jill Duffy of PC Magazine gave a review of the app, pointing out its key features, and stating that the app is great if you enjoy listening to different, or new music, that can match your tempo while running. Also in 2015, Digital Trends listed RockMyRun, as one of the best exercise music apps in the article "No need to make exercise playlists with these music apps". In 2018, Redbull.com recommended RockMyRun in preparation for the Wings for Life World Run in their article "10 essential hacks for running to work to get you in World Run shape". In 2019, The Fashion Spot included RockMyRun in their list of "The Best Workout Apps for People Who Hate to Work Out", saying: "RockMyRun matches music to the tempo of your running pace – the music literally follows your steps/heart rate. The app has thousands of mixes/music options along with tracking capabilities." Also in 2019, MakeUseOf.com included RockMyRun in their list of "The 7 Best Running and Workout Music Apps". In September 2022, VeryWellFit listed RockMyRun as the first of three "Other Playlist Options" in the article "How to Create a Running Playlist, According to Running Coaches". Tech Grapple recommended the app in "The best workout free music apps for iPhone and Android" saying that "RockMyRun is the best application that you can use during workout. It comes with amazing DJs to craft mixes that will keep you moving." == Partners == RockMyRun is partnered with the following brands/companies: C25K Del Taco JLab Audio iFit Active Network, LLC Night Nation Run (the world's first running music festival) Lady Foot Locker Mayweather Boxing + Fitness Mio Global Orangetheory Fitness Red Rock Apps Tapout Fitness
MSpy
mSpy is a brand of mobile and computer parental control monitoring software for iOS, Android, Windows, and macOS. The app monitors and logs user activity on the client device and sends the data to a personalized dashboard. Data the users can monitor includes text messages, calls, GPS locations, social media chats, and more. It is owned by Virtuoso Holding. == History == mSpy was launched as a product for mobile monitoring by Altercon Group in 2010. In 2012, the application allowed parents to monitor not only smartphones but also computers running Windows and macOS. In 2013, mSpy became TopTenReviews cell phone monitoring software award winner. By 2014, the business grew nearly 400%, and the app's user numbers exceeded 1 million. In 2015, mSpy received the Parents Tested Parents Approved (PTPA) Winner’s Seal of Approval in the United States. In 2015 and 2018, mSpy was the victim of data breaches which released user data. In 2016, mLite, a light version of mSpy, became available from Google Play. The same year, it was awarded the kidSAFE Certified Seal in the United States. In 2017, mSpy collaborated with YouTuber and journalist Coby Persin to conduct a social experiment on the dangers of social media and online predators. A social experiment, conducted with parental consent, involved Coby Persin to befriend three children—aged 12, 13, and 14—via Snapchat and then invite them to meet personally. Each of the participants agreed to the meeting and arrived at the designated location. The video of the experiment received widespread attention and helped to raise awareness about the importance of online security and parental controls. In early 2021, mSpy released a new feature - Screenrecorder. The feature allows parents to take screenshots of the kid's screen when they are browsing certain apps. In 2024, mSpy's Zendesk was compromised by an unknown threat actor, revealing their customer list. As of 2025, mSpy is compatible with Android, iPhone, and iPad devices. It provides access to various types of data stored on the device, including contact information, calendar entries, emails, SMS messages, browser history, photos, videos, and installed applications. Functions also include GPS tracking, geofencing, keyword alerts etc. == Reception == It was noted that since MSpy runs inconspicuously, there is risk of the software being used illegally. mSpy was called "terrifying" by The Next Web and was featured in NPR coverage of spyware used against victims of stalking and other domestic violence. In response mSpy released security updates aimed at reducing the risk of misuse and stated that it "uses encryption protocols to protect user data and that access is restricted to the account holder". In May 2015, Brian Krebs reported that mSpy was hacked, leaking personal data for hundreds of thousands of users of devices with mSpy installed. mSpy claimed that there was no data leak, but that instead, it was the victim of blackmailers. In September 2018, Krebs claimed and demonstrated that anyone could easily gain access to the mSpy database containing data for millions of users. The company responded by stating that the exposed data consisted primarily of error logs and incorrect login attempts. Following the incident, mSpy implemented new security measures, changed encryption keys, and reset passwords for affected accounts. A 2024 Sky News story characterised mSpy as "stalkerware". Leaked customer support messages from mSpy reveal misuse of its app for illegally monitoring partners and children.
Digital Michelangelo Project
The Digital Michelangelo Project was a pioneering initiative undertaken during the 1998–1999 academic year to digitize the sculptures and architecture of Michelangelo using advanced laser scanning technology. The project was led by a team of 30 faculty, staff, and students from Stanford University and the University of Washington, with the aim of creating high-resolution 3D models of Michelangelo's works for scholarly, educational, and preservation purposes. == Objectives == The primary goals of the Digital Michelangelo Project were: To apply recent advancements in laser rangefinder technology for digitizing large cultural artifacts. To create detailed digital archives of Michelangelo's sculptures and architectural spaces for future study and analysis. To explore potential educational and curatorial applications for 3D scanned data. === Artworks digitized === The project involved scanning several iconic works by Michelangelo, including: David The Unfinished Slaves (Atlas, Awakening, Bearded, and Youthful) St. Matthew The allegorical statues from the Medici tombs (Night, Day, Dawn, and Dusk) The architectural interiors of the Tribuna del David at the Galleria dell'Accademia and the New Sacristy in the Medici Chapels. == Technology and methodology == === 3D scanning === The project's primary scanner was a laser triangulation rangefinder mounted on a motorized gantry, custom-built by Cyberware Inc. The scanner used a laser sheet to project onto an object, capturing its shape through triangulation. Multiple scans were taken from various angles and combined into a single, detailed 3D mesh. The resolution achieved was fine enough to capture even Michelangelo's chisel marks, with triangles approximately 0.25 mm on each side. In addition to shape data, color data was captured using a spotlight and a secondary camera, enabling the creation of textured 3D models. === Data processing === The project developed a software suite for processing the scanned data. This included: Aligning and merging multiple scans into a seamless 3D model. Filling holes in the geometry caused by inaccessible areas. Correcting color data for lighting inconsistencies and shadowing. Non-photorealistic rendering techniques were also applied, highlighting surface features such as Michelangelo’s chisel marks for enhanced visualization. == Logistical challenges == The scale and complexity of the project presented several challenges: Data size: The dataset for David alone comprised 2 billion polygons and 7,000 color images, occupying 60 GB of storage. Artifact safety: Ensuring the safety of the statues during scanning required extensive crew training, foam-encased equipment, and collision-prevention mechanisms. == Applications and impact == The digitized models have numerous potential applications: Art history: Allowing precise measurements and geometric analysis, such as determining chisel types or evaluating structural balance. Education: Providing new ways to study art, including interactive viewing from unconventional angles and with custom lighting. Museum curation: Enhancing visitor experiences through interactive kiosks and virtual models. The project demonstrated the potential for 3D technology to preserve and disseminate cultural heritage. == Data distribution == The project's models are available through Stanford University for scholarly purposes, under strict licensing due to Italian intellectual property laws. === ScanView === To provide public access to the 3D models while respecting usage restrictions, the project developed ScanView, a client/server rendering system. ScanView allows users to view and interact with high-resolution 3D models without downloading the data. The client component consists of a freely available viewer program and simplified 3D models. Users can navigate these models locally, adjusting position, orientation, lighting, and surface appearance. When a user finalizes a view, the client queries a remote server for a high-resolution rendering of the model, which is sent back to overwrite the simplified version on the user’s screen. A typical query-response cycle takes 1–2 seconds, depending on network conditions. To protect the models from unauthorized reconstruction, the system employs several security measures, including: Encrypting queries Perturbing viewpoint and lighting parameters Adding noise and warping rendered images Compressing images before transmission ScanView operates on Windows-based PCs and provides access to selected models, including David and St. Matthew, as well as other artifacts such as fragments of the Forma Urbis Romae and items from the Stanford 3D Scanning Repository. == Sponsors == The Digital Michelangelo Project was supported by Stanford University, Interval Research Corporation, and the Paul G. Allen Foundation for the Arts.
Texture compression
Texture compression is a specialized form of image compression designed for storing texture maps in 3D computer graphics rendering systems. Unlike conventional image compression algorithms, texture compression algorithms are optimized for random access. Texture compression can be applied to reduce memory usage at runtime. Texture data is often the largest source of memory usage in a mobile application. == Tradeoffs == In their seminal paper on texture compression, Beers, Agrawala and Chaddha list four features that tend to differentiate texture compression from other image compression techniques. These features are: Decoding Speed It is highly desirable to be able to render directly from the compressed texture data and so, in order not to impact rendering performance, decompression must be fast. Random Access Since predicting the order that a renderer accesses texels would be difficult, any texture compression scheme must allow fast random access to decompressed texture data. This tends to rule out many better-known image compression schemes such as JPEG or run-length encoding. Compression Rate and Visual Quality In a rendering system, lossy compression can be more tolerable than for other use cases. Some texture compression libraries, such as crunch, allow the developer to flexibly trade off compression rate vs. visual quality, using methods such as rate–distortion optimization (RDO). Encoding Speed Texture compression is more tolerant of asymmetric encoding/decoding rates as the encoding process is often done only once during the application authoring process. Given the above, most texture compression algorithms involve some form of fixed-rate lossy vector quantization of small fixed-size blocks of pixels into small fixed-size blocks of coding bits, sometimes with additional extra pre-processing and post-processing steps. Block Truncation Coding is a very simple example of this family of algorithms. Because their data access patterns are well-defined, texture decompression may be executed on-the-fly during rendering as part of the overall graphics pipeline, reducing overall bandwidth and storage needs throughout the graphics system. As well as texture maps, texture compression may also be used to encode other kinds of rendering map, including bump maps and surface normal maps. Texture compression may also be used together with other forms of map processing such as mipmaps and anisotropic filtering. == Availability == Some examples of practical texture compression systems are S3 Texture Compression (S3TC), PVRTC, Ericsson Texture Compression (ETC) and Adaptive Scalable Texture Compression (ASTC); these may be supported by special function units in modern graphics processing units (GPUs). OpenGL and OpenGL ES, as implemented on many video accelerator cards and mobile GPUs, can support multiple common kinds of texture compression - generally through the use of vendor extensions. == Supercompression == A compressed-texture can be further compressed in what is called "supercompression". Fixed-rate texture compression formats are optimized for random access and are much less efficient compared to image formats such as PNG. By adding further compression, a programmer can reduce the efficiency gap. The extra layer can be decompressed by the CPU so that the GPU receives a normal compressed texture, or in newer methods, decompressed by the GPU itself. Supercompression saves the same amount of VRAM as regular texture compression, but saves more disk space and download size. == Neural Texture Compression == Random-Access Neural Compression of Material Textures (Neural Texture Compression) is a Nvidia's technology which enables two additional levels of detail (16× more texels, so four times higher resolution) while maintaining similar storage requirements as traditional texture compression methods. The key idea is compressing multiple material textures and their mipmap chains together, and using a small neural network, that is optimized for each material, to decompress them.