AI Assistant Jetbrains Plugin

AI Assistant Jetbrains Plugin — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Color picker

A color picker (also color chooser or color tool) is a graphical user interface widget, usually found within graphics software or online, used to select colors and, in some cases, to create color schemes (the color picker might be more sophisticated than the palette included with the program). Operating systems such as Microsoft Windows or macOS have a system color picker, which can be used by third-party programs (e.g., Adobe Photoshop). == History == The concept of color pickers dates back to the early days of computer graphics and digital design. Early versions were rudimentary, often featuring basic color palettes and limited functionality. One of the first drawing programs to include a color picker was SketchPad (also referred to as LisaSketch), designed by Bill Atkinson in 1983 to showcase LisaGraf's capabilities. It used a black and white pattern system, using dithering to create the illusion of color depth. With the increased popularity of personal computers with color graphics, there soon came software similar to SketchPad that supported more than two colors, like Broderbund's Dazzle Draw for the Apple II or Electronic Arts' Deluxe Paint. However, the color pickers present in those programs relied on indexed colors. Color pickers, resembling ones used in modern software with support for direct, 24-bit color, appeared soon after the release of the Macintosh II, with the release of programs like Adobe Photoshop and Corel Painter. As the increase of color depth allowed the choice of significantly more colors, the shape and form of color pickers started to diverge. For example, Adobe Photoshop used a hue-saturation color wheel with a slider for brightness in version 0.63, later on switching to a rectangular design accompanied by a hue slider. Corel Painter pioneered the triangular saturation and brightness picker with a hue ring around it, aiming to better represent the continuity of the hue spectrum and the relationship between saturation and brightness. == Purpose == A color picker is used to select and adjust color values. In graphic design and image editing, users typically choose colors via an interface with a visual representation of a color—organized with quasi-perceptually-relevant hue, saturation and lightness dimensions (HSL) – instead of keying in alphanumeric text values. Because color appearance depends on comparison of neighboring colors (see color vision), many interfaces attempt to clarify the relationships between colors. == Interface == Color tools can vary in their interface. Some may use sliders, buttons, text boxes for color values, or direct manipulation. Often a two-dimensional square is used to create a range of color values (such as lightness and saturation) that can be clicked on or selected in some other manner. Drag and drop, color droppers, and various other forms of interfaces are commonly used as well. Usually, color values are also displayed numerically, so they can be precisely remembered and keyed-in later, such as three values of 0-255 representing red, green, and blue, respectively. === Eyedropper === The eyedropper is a tool present in most color pickers and graphics software that allows a user to read a color at a specific point in an image, or position on a display. This enables the color to be transferred to other applications particularly quickly. Modern implementations of eyedropper tools are also available as browser extensions, allowing users to pick colors directly from web pages, such as in Google Chrome and Microsoft Edge. == Working == A color picker has two main parts, first a color slider and second a color canvas. The color slider has a linear or radial gradient of the seven rainbow colors i.e. Violet, Indigo, Blue, Green, Yellow, Orange and Red. It allows one to choose any of the seven primary colors. The color value chosen from the color slider instantly reflects in the color canvas. The color canvas is a mixture of two linear color gradients. First a linear gradient of the current chosen color and second a linear gradient of the black color. This mixture of color gradients lets one choose a lighter and darker version of the current chosen color from the color slider.
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 →
OpenNN

OpenNN (Open Neural Networks Library) is a software library written in the C++ programming language which implements neural networks, a main area of deep learning research. The library is open-source, licensed under the GNU Lesser General Public License. == Characteristics == The software implements any number of layers of non-linear processing units for supervised learning. This deep architecture allows the design of neural networks with universal approximation properties. Additionally, it allows multiprocessing programming by means of OpenMP, in order to increase computer performance. OpenNN contains machine learning algorithms as a bundle of functions. These can be embedded in other software tools, using an application programming interface, for the integration of the predictive analytics tasks. In this regard, a graphical user interface is missing but some functions can be supported by specific visualization tools. == History == The development started in 2003 at the International Center for Numerical Methods in Engineering, within the research project funded by the European Union called RAMFLOOD (Risk Assessment and Management of FLOODs). Then it continued as part of similar projects. OpenNN is being developed by the startup company Artelnics. == Applications == OpenNN is a general purpose artificial intelligence software package. It uses machine learning techniques for solving predictive analytics tasks in different fields. For instance, the library has been applied in the engineering, energy, or chemistry sectors.
Read more →
Emospark

EmoSpark is an artificial intelligence console created in London, United Kingdom by Patrick Levy-Rosenthal. The device uses facial recognition and language analysis to evaluate human emotion and convey responsive content according to the emotion. The console measures 90 mm x 90 mm x 90 mm and is cube shaped. It operates on an "Emotional Processing Unit", an emotion chip developed by Emoshape Inc. that enables the system to create emotional profile graphs of its surroundings. The emotional processing unit is a patent pending technology that is said to create synthesised emotional responses in machines. EmoSpark was funded through an Indiegogo campaign which aimed to raise $200,000. == Product overview == EmoSpark was created by French inventor Patrick Levy-Rosenthal, as an emotionally intelligent artificial life unit for the home that can interact with people. It is powered by Android and can communicate with users through typed input from a computer, tablet, smartphone or TV as well as through spoken commands. The EmoSpark's features are categorized into two types: functional and emotional. EmoSpark is said to have the ability to perform practical software-based tasks. Through the smartphone interface, it is able to gauge a person’s emotions and is reported to have a conversational library of over 2 million sentences. The face-tracking technology identifies users likes and dislikes to categorize their emotional responses to stimuli such as videos and music. The device has an emotional spectrum that is composed of eight emotions which are surprise, sadness, joy, trust, fear, disgust, anger and anticipation. EmoSpark monitors a person's facial expressions and emotions through images from an external camera, which are then processed through an emotion text analysis and content analysis. The New Scientist reported that EmoSpark had the ability to work on the best way to cheer up its users, emotionally. === Connectivity === EmoSpark is able to connect to Facebook and YouTube to present users with content designed to improve their mood, or to Wikipedia for collaborative knowledge that can be shared when users ask questions of it. Through Android OS, EmoSpark is able to be customized with Google Play store apps. The cube is expected to develop its own personality based on the communications it has had with the people using it. == EmoShape == The Emotion Chip (EPU) used in the cube is created by the US company Emoshape Inc, founded by Levy-Rosenthal. EmoShape Ltd (UK) was the company that developed EmoSpark cube. Patrick Levy-Rosenthal also received the IST Prize in 2005 from the European Council for Applied Science, Technology and Engineering.
Read more →
Language Computer Corporation

Language Computer Corporation (LCC) is a natural language processing research company based in Richardson, Texas. The company develops a variety of natural language processing products, including software for question answering, information extraction, and automatic summarization. Since its founding in 1995, the low-profile company has landed significant United States Government contracts, with $8,353,476 in contracts in 2006-2008. While the company has focused primarily on the government software market, LCC has also used its technology to spin off three start-up companies. The first spin-off, known as Lymba Corporation, markets the PowerAnswer question answering product originally developed at LCC. In 2010, LCC's CEO, Andrew Hickl, co-founded two start-ups which made use of the company's technology. These included Swingly, an automatic question answering start-up, and Extractiv, an information extraction service that was founded in partnership with Houston, Texas-based 80legs.
Read more →
Blockhead (thought experiment)

Blockhead is a theoretical computer system invented as part of a thought experiment by philosopher Ned Block, which appeared in a paper titled "Psychologism and Behaviorism". Block did not personally name the computer in the paper. == Overview == In "Psychologism and Behaviorism", Block argues that the internal mechanism of a system is important in determining whether that system is intelligent and claims to show that a non-intelligent system could pass the Turing test. Block asks the reader to imagine a conversation lasting any given amount of time. He states that given the nature of language, there are a finite number of syntactically and grammatically correct sentences that can be used to start a conversation. Consequently, there is a limit to how many "sensible" responses can be made to the first sentence, then to the second sentence, and so on until the conversation ends. Block then asks the reader to imagine a computer which had been programmed with all the sentences in theory, if not in practice. Block argues that such a machine could continue a conversation with a person on any topic because the computer would be programmed with every sentence that it was possible to use so the computer would be able to pass the Turing test despite the fact that—according to Block—it was not intelligent. Block says that this does not show that there is only one correct internal structure for generating intelligence but simply that some internal structures do not generate intelligence. The argument is related to John Searle's Chinese room.
Read more →
Microelectronics and Computer Technology Corporation

Microelectronics and Computer Technology Corporation, originally the Microelectronics and Computer Consortium and widely seen by the acronym MCC, was the first, and at one time one of the largest, computer industry research and development consortia in the United States. MCC ceased operations in 2000 and was formally dissolved in 2004. == Divisions == MCC did research and development in the following areas: [1] System Architecture and Design (optimise hardware and software design, provide for scalability and interoperability, allow rapid prototyping for improved time-to-market, and support the re-engineering of existing systems for open systems). Advanced Microelectronics Packaging and Interconnection (smaller, faster, more powerful, and cost-competitive). Hardware Systems Engineering (tools and methodologies for cost-efficient, up-front design of advanced electronic systems, including modelling and design-for-test techniques to improve cost, yield, quality, and time-to-market). Environmentally Conscious Technologies (process control and optimisation tools, information management and analysis capabilities, and non-hazardous material alternatives supporting cost-efficient production, waste minimisation, and reduced environmental impact). Distributed Information Technology (managing and maintaining physically distributed corporate information resources on different platforms, building blocks for the national information infrastructure, networking tools and services for integration within and between companies, and electronic commerce). Intelligent Systems (systems that "intelligently" support business processes and enhance performance, including decision support, data management, forecasting and prediction). == History == The MCC was a response to the announcement of Japan's Fifth Generation Project, a large Japanese research project launched in 1982 aimed at producing a new kind of computer by 1991. The Japanese had formed similar industrial research consortia as early as 1956.[2] Many European and American computer companies saw this new Japanese initiative as an attempt to take full control of the world's high-end computer market, and MCC was created, in part, as a defensive move against that threat. In late 1982, several major computer and semiconductor manufacturers in the United States banded together and founded MCC under the leadership of Admiral Bobby Ray Inman, whose previous positions had been Director of the National Security Agency and deputy director of the Central Intelligence Agency. Such formations were illegal in the United States until the 1984 Congressional passage of the "National Cooperative Research Act". Several sites with relevant universities were considered, including Atlanta, Georgia (Georgia Tech), the Research Triangle, N.C. (UNC), the Washington, D.C. area (George Mason), Stanford University and Austin, Texas (UT) which was the final selection. The University of Texas offered land upon which they would construct a new building specifically designed for the MCC within their Austin campus. Ross Perot also offered the use of his private plane for 2 years for staff recruitment. Austin was selected as the site for MCC in 1983. Despite this purpose and the background of Inman and his senior staff, MCC accepted no government funding for many years and was a refuge for some avoiding work on Strategic Defense Initiative projects. MCC was part of the Artificial Intelligence boom of the 1980s, reportedly the single largest customer of both Symbolics and Lisp Machines, Inc. (and like Symbolics, was one of the first companies to register a .com domain). In the 1980s its major programs were packaging, software engineering, CAD, and advanced computer architectures. The latter comprised artificial intelligence, human interface, database, and parallel processing, the latter two merging in the late 1980s. Many of the early shareholder companies were mainframe computer companies under stress in the 1980s. Over the years, MCC's membership diversified to include a broad range of high-profile corporations involved in information technology products, as well as government research and development agencies and leading universities. In June, 2000 the MCC Board of Directors voted to dissolve the consortium, and the few remaining employees held a wake at Scholz's Beer Garden in Austin on October 25. Formal dissolution papers were reportedly not filed until 2004. == Spinoffs == While multiple technologies were transferred to member companies and government agencies in the final years, fourteen companies were spun out of MCC. Those spinoffs include: TeraVicta Technologies, Austin's first MEMS company; its focus was to develop microscopic switch technology for fiber optic switching and radiofrequency switching in mobile phones specifically to dynamically switch between the future 3G-4GLTE-future5G wireless communication frequencies and ensure mobile phones were communicating over the strongest wireless signal to reduce dropped calls. Robert Miracky was the founding CEO who spun out the first commercial metal micromachining technology developed by MCC researchers Brent Lunceford, Jason Reed, Richard Nelson, K.Hu, and C. Hilbert in a collaborative development program with IBM in a novel implementation and operational paradigm for solid-state integrated circuit coolers integrated with conductive MEMS switches. TeraVicta was liquidated under Chapter 7 bankruptcy proceedings in 2015. The Austin region subsequently built up a MEMS & Sensors value chain in the billions of dollars comprising companies such as 3M, Cypress Semiconductor, NXP Semiconductor, Cirrus Logic, Silicon Labs, and the Austin division of the now-defunct Silicon Valley Technology Center. Portelligent, a company that provides reverse engineering teardown services. At the time, Portelligent was the first company to commercialize such services; they had been provided by MCC to its member companies. Today, there are at least twelve companies worldwide that sell reports known as "reverse engineering teardown reports." Modern day teardown reports provide detailed information about technology products such as the bill of materials, microchip, and printed circuit board design specifics, manufacturing details including manufacturing location details for the entire value chain responsible for making electronics, including the iPhone and Samsung Galaxy smartphones. Portelligent was acquired by CMP Technology in 2007. Evolutionary Technologies International, a company focused on developing database tools and data warehousing. It was spun off from MCC in 1990.
Read more →
REEM

REEM is a prototype humanoid robot built by PAL Robotics in Spain. It is a 1.70 m high humanoid robot with 22 degrees of freedom, with a mobile base with wheels, allowing it to move at 4 km/hour. The upper part of the robot consists of a torso with a touch screen, two motorized arms, which give it a high degree of expression, and a head, which is also motorized. REEM-A and REEM-B are the first and second prototypes of humanoid robots created by PAL Robotics. REEM-B can recognize, grasp and lift objects and walk by itself, avoiding obstacles through simultaneous localization and mapping. The robot accepts voice commands and can recognize faces. == Specifications ==
Read more →
DaVinci (software)

DaVinci was a development tool produced by Incross, which aimed at creating HTML5 mobile applications and media content. It included a jQuery framework and a JavaScript library that enabled developers and designers to craft web applications designed for mobile devices with a user experience similar to native applications. Business applications, games, rich media content, such as HTML5 multi-media magazines, advertisements, and animation, may be produced with the tool. DaVinci was based on standard web technology – including HTML5, CSS3, and JavaScript. == Features == DaVinci comprised DaVinci Studio and DaVinci Animator, which handled application programming and UI design. The tool had a WYSIWYG authoring environment. Open-source libraries, such as KnockOut, JsRender/JsViews, Impress.js, and turn.js, were included in the tool. Other open-source frameworks could also be integrated. The Model View Controller (MVC) and Data Binding in JavaScript could be handled through DaVinci's Data-Set Editor. In this mode, view components and model data could be visually bound, which allowed users to create web applications with server-integrated UI components without coding. Additionally, DaVinci included an N-Screen editor, which automatically adjusted designs and functionalities to fit the screen sizes of various devices, including smartphones, tablet PCs, and TVs. == DaVinci and jQuery == In collaboration with the jQuery Foundation, DaVinci played a significant role in hosting the first jQuery conference in an Asian district, which took place on November 12, 2012, in Seoul, South Korea. The conference showcased how DaVinci could be utilized in application development demonstrations.
Read more →
GPT-5.3-Codex

GPT-5.3-Codex (Generative Pre-trained Transformer 5.3 Codex) is a large language model (LLM) announced and released by OpenAI on February 5, 2026. It is made as a competitor to Claude's Opus 4.6, focusing on code generation, speed and the ability to search repositories, run terminal commands and at the same time, debug code. In technical benchmarks, it is reported that GPT-5.3 Codex is 25% faster than Opus 4.6. GPT-5.3 Codex is available in the Codex app and on the web; access via API is also planned. According to OpenAI, GPT-5.3-Codex is the company's "first model that was instrumental in creating itself." On February 12, 2026, GPT-5.3-Codex-Spark was released in a research preview, which is a smaller version of GPT-5.3-Codex which supports text-only input. As of February 2026, GPT-5.3-Codex is only available for ChatGPT Pro ($200/month) subscribers.
Read more →
Lukas Biewald

Lukas Biewald (born 1981) is an American entrepreneur and a prominent figure in artificial intelligence. He is recognized for his contributions to machine learning and as the CEO and co-founder of Weights & Biases, a company that builds developer tools for AI, that sold to CoreWeave in 2025 for $1.7B. He previously founded and was CEO of Figure Eight, a human-in-the-loop machine learning platform. He has co-authored 26 AI research papers from 2004 through 2018. == Early life and education == Biewald was born in Boston, Massachusetts in 1981. He attended Cambridge Rindge and Latin School and later earned both a Bachelor's and Master's degree in Computer science from Stanford University. == Early Career and Founding Figure Eight == After graduation, Biewald joined Yahoo! as an engineer, working on machine translations to improve search results, and eventually led the Search Relevance Team for Yahoo! Japan. He later joined Powerset, a natural language search technology company, as their Senior Scientist, which was acquired by Microsoft in 2008 for an estimated $100M. In 2007, Biewald co-founded Figure Eight (formerly CrowdFlower), a data labeling and crowdsourcing company that created datasets for training machine learning models. Figure Eight was acquired by Appen in 2019 for $300 million. == Weights and Biases == In 2017, Biewald co-founded Weights & Biases with Chris Van Pelt and Shawn Lewis. The company provides tools for tracking machine learning experiments, model management, and collaborative AI and LLM app development. The platform has been adopted by organizations such as OpenAI, Salesforce, and Microsoft. In March 2025 Coreweave acquired Weights and Biases at $1.7 billion, with the transaction closing on May 5, 2025. == Gradient Dissent == Biewald hosts the bi-weekly podcast Gradient Dissent. Guest have included: Anthony Goldbloom – Co-founder & CEO of Kaggle. “How to Win Kaggle Competitions” (podcast, Sep. 9, 2020). Shared tips on data-science competitions from the founder of the largest ML community. Richard Socher – Founder & CEO of You.com; former Chief Scientist at Salesforce. “The Challenges of Making ML Work in the Real World” (podcast, September 28, 2020). A leading NLP researcher, he spoke on multimodal search engines powered by large language models. Jensen Huang – Founder & CEO of NVIDIA. “NVIDIA’s CEO on the Next Generation of AI and MLOps” (podcast, March 3, 2022). Huang’s GPUs power modern ML research and production. Emad Mostaque – Co-founder & CEO of Stability AI. “Stable Diffusion, Stability AI, and What’s Next” (podcast, Nov. 15, 2022). Leads the company behind Stable Diffusion, which helped spark the generative-AI imaging boom. Drago Anguelov – Head of Research at Waymo. “Robustness, Safety, and Scalability at Waymo” (podcast, July 14, 2022). Covered Waymo’s self-driving AI advances and deployment challenges. Jeremy Howard – Co-founder of fast.ai. “The Simple but Profound Insight Behind Diffusion” (podcast, Jan. 5, 2023). Known for democratizing deep-learning education; discussed diffusion models and accessible AI tooling. Aidan Gomez – Co-founder & CEO of Cohere. “Scaling LLMs and Accelerating Adoption” (podcast, April 20, 2023). Co-author of “Attention Is All You Need,” he shared how Cohere delivers large-scale NLP models as a service. Chelsea Finn – Stanford Assistant Professor (AI & Robotics). “Shaping the World of Robotics with Chelsea Finn” (podcast, February 15, 2024). A pioneer in meta-learning and robotics, she detailed robots learning complex tasks like cooking. Andrew Feldman – Co-founder & CEO of Cerebras Systems. "Launching the Fastest AI Inference Solution" (podcast, August 27, 2024). Described wafer-scale AI chips achieving new training performance records. Thomas Dohmke – CEO of GitHub. “GitHub CEO on Copilot and the Future of Software Development” (podcast, June 10, 2025). Discussed building Copilot and the future of AI-assisted coding. Martin Shkreli – Founder of Godel Terminal. “From Pharma to AGI Hype, and Developing AI in Finance: Martin Shkreli’s Journey” (podcast, May 20, 2025). Shkreli reflects on his pharma controversies, prison experience, and his new AI-driven trading platform. Jarek Kutylowski – Founder & CEO of DeepL. “How DeepL Built a Translation Powerhouse with AI” (podcast, July 8, 2025). Shared how DeepL’s neural-MT rivals Google Translate through model and infrastructure innovation. == Awards and recognition == In 2010, Lukas Biewald won the Netexplorateur Award for creating the GiveWork iPhone app, which allows users to perform small tasks that assist refugees and people in developing countries. In 2010, Inc Magazine included Biewald and Van Pelt on its list of the Top 30 Entrepreneurs Under 30. == Publications == Ensuring quality in crowdsourced search relevance evaluation: The effects of training question distribution by John Le, Andy Edmonds, Vaughn Hester, Lukas Biewald. SIGIR 2010 Workshop on Crowdsourcing for Search Evaluation, July 2010. Superficial Data Analysis: Exploring Millions of Social Stereotypes by Lukas Biewald, Brendan O’Connor. O’Reilly July 2009 Biewald has co-authored 26 AI research papers from 2004 through 2018.
Read more →
Minimum information standard

Minimum information standards are sets of guidelines and formats for reporting data derived by specific high-throughput methods. Their purpose is to ensure the data generated by these methods can be easily verified, analysed and interpreted by the wider scientific community. Ultimately, they facilitate the transfer of data from journal articles (unstructured data) into databases (structured data) in a form that enables data to be mined across multiple data sets. Minimal information standards are available for a vast variety of experiment types including microarray (MIAME), RNAseq (MINSEQE), metabolomics (MSI) and proteomics (MIAPE). Minimum information standards typically have two parts. Firstly, there is a set of reporting requirements – typically presented as a table or a checklist. Secondly, there is a data format. Information about an experiment needs to be converted into the appropriate data format for it to be submitted to the relevant database. In the case of MIAME, the data format is provided in spreadsheet format (MAGE-TAB). Some of the communities that maintain minimum information standards also provide tools to help experimental researchers to annotate their data. == MI Standards == The individual minimum information standards are brought by the communities of cross-disciplinary specialists focused on the problematic of the specific method used in experimental biology. The standards then provide specifications what information about the experiments (metadata) is crucial and important to be reported together with the resultant data to make it comprehensive. The need for this standardization is largely driven by the development of high-throughput experimental methods that provide tremendous amounts of data. The development of minimum information standards of different methods is since 2008 being harmonized by "Minimum Information about a Biomedical or Biological Investigation" (MIBBI) project. === MIAPPE, Minimum Information About a Plant Phenotyping Experiment === MIAPPE is an open, community driven project to harmonize data from plant phenotyping experiments. MIAPPE comprises both a conceptual checklist of metadata required to adequately describe a plant phenotyping experiment. === MIQE, Minimum Information for Publication of Quantitative Real-Time PCR Experiments === Published in 2009 these guidelines for the basis of requirements by many journals when submitting QPCR data, sadly they are not adhered to enough. === MIAME, gene expression microarray === Minimum Information About a Microarray Experiment (MIAME) describes the Minimum Information About a Microarray Experiment that is needed to enable the interpretation of the results of the experiment unambiguously and potentially to reproduce the experiment and is aimed at facilitating the dissemination of data from microarray experiments. It was published by the FGED Society in 2001 and was the first published minimum information standard for high-throughput experiments in the life sciences. MIAME contains a number of extensions to cover specific biological domains, including MIAME-env, MIAME-nut and MIAME-tox, covering environmental genomics, nutritional genomics and toxogenomics, respectively. === MINI: Minimum Information about a Neuroscience Investigation === ==== MINI: Electrophysiology ==== Electrophysiology is a technology used to study the electrical properties of biological cells and tissues. Electrophysiology typically involves the measurements of voltage change or electric current flow on a wide variety of scales from single ion channel proteins to whole tissues. This document is a single module, as part of the Minimum Information about a Neuroscience investigation (MINI) family of reporting guideline documents, produced by community consultation and continually available for public comment. A MINI module represents the minimum information that should be reported about a dataset to facilitate computational access and analysis to allow a reader to interpret and critically evaluate the processes performed and the conclusions reached, and to support their experimental corroboration. In practice a MINI module comprises a checklist of information that should be provided (for example about the protocols employed) when a data set is described for publication. The full specification of the MINI module can be found here. === MIARE, RNAi experiment === Minimum Information About an RNAi Experiment (MIARE) is a data reporting guideline which describes the minimum information that should be reported about an RNAi experiment to enable the unambiguous interpretation and reproduction of the results. === MIACA, cell based assay === Advances in genomics and functional genomics have enabled large-scale analyses of gene and protein function by means of high-throughput cell biological analyses. Thereby, cells in culture can be perturbed in vitro and the induced effects recorded and analyzed. Perturbations can be triggered in several ways, for instance with molecules (siRNAs, expression constructs, small chemical compounds, ligands for receptors, etc.), through environmental stresses (such as temperature shift, serum starvation, oxygen deprivation, etc.), or combinations thereof. The cellular responses to such perturbations are analyzed in order to identify molecular events in the biological processes addressed and understand biological principles. We propose the Minimum Information About a Cellular Assay (MIACA) for reporting a cellular assay, and CA-OM, the modular cellular assay object model, to facilitate exchange of data and accompanying information, and to compare and integrate data that originate from different, albeit complementary approaches, and to elucidate higher order principles. Documents describing MIACA are available and provide further information as well as the checklist of terms that should be reported. === MIAPE, proteomic experiments === The Minimum Information About a Proteomic Experiment documents describe information which should be given along with a proteomic experiment. The parent document describes the processes and principles underpinning the development of a series of domain specific documents which now cover all aspects of a MS-based proteomics workflow. === MIMIx, molecular interactions === This document has been developed and maintained by the Molecular Interaction worktrack of the HUPO-PSI (www.psidev.info) and describes the Minimum Information about a Molecular Interaction experiment. === MIAPAR, protein affinity reagents === The Minimum Information About a Protein Affinity Reagent has been developed and maintained by the Molecular Interaction worktrack of the HUPO-PSI (www.psidev.info)in conjunction with the HUPO Antibody Initiative and a European consortium of binder producers and seeks to encourage users to improve their description of binding reagents, such as antibodies, used in the process of protein identification. === MIABE, bioactive entities === The Minimum Information About a Bioactive Entity was produced by representatives from both large pharma and academia who are looking to improve the description of usually small molecules which bind to, and potentially modulate the activity of, specific targets in a living organism. This document encompasses drug-like molecules as well as herbicides, pesticides and food additives. It is primarily maintained through the EMBL-EBI Industry program (www.ebi.ac.uk/industry). === MIGS/MIMS, genome/metagenome sequences === This specification is being developed by the Genomic Standards Consortium === MIFlowCyt, flow cytometry === === Minimum Information about a Flow Cytometry Experiment === The Minimum Information about a Flow Cytometry Experiment (MIFlowCyt) is a standard related to flow cytometry which establishes criteria to record information on experimental overview, samples, instrumentation and data analysis. It promotes consistent annotation of clinical, biological and technical issues surrounding a flow cytometry experiment. === MINDR, dual gene expression reporters === Requires (1) reporting absolute values of reporter readouts, (2) list of positive and negative controls, and (3) sequences of all reporter constructs. === MISFISHIE, In Situ Hybridization and Immunohistochemistry Experiments === === MIAPA, Phylogenetic Analysis === Criteria for Minimum Information About a Phylogenetic Analysis were described in 2006. === MIRAGE, Glycomics === The MIRAGE project is supported and coordinated by the Beilstein-Institut to establish guidelines for data handling and processing in glycomics research [1] === MIAO, ORF === === MIAMET, METabolomics experiment === === MIAFGE, Functional Genomics Experiment === === MIRIAM, Minimum Information Required in the Annotation of Models === The Minimal Information Required In the Annotation of Models (MIRIAM), is a set of rules for the curation and annotation of quantitative models of biological systems. === MIASE, Minimum Information About a Simulation Experiment =
Read more →
Scripped

Scripped was an online screenplay services company offering three services: script writing, script registration, and script coverage. Scripped did not facilitate collaboration among screenwriters. It combined with Zhura in 2010. According to Techcrunch, Scripped had more than 60,000 writers as of March 2010. Scripped was administered by Sunil Rajaraman, Ryan Buckley and Zak Freer. Actor, writer, and director Edward Burns and screenwriter Steven E. de Souza joined Scripped's Board of Advisers in May 2008. In 2008, the company formed a partnership with Write Brothers, makers of Movie Magic Screenwriter software. On March 29, 2010, Scripped announced that it closed $250,000 in private investment and merged with competitor Zhura. Scripped's CEO, Sunil Rajaraman, remains the merged company's Chief Executive Officer. On April 1, 2015, citing a serious technical failure, Scripped shuttered its service. As part of the announcement, it was disclosed that their backup servers had failed as well, losing all of its users' stored scripts. The website URL currently redirects to WriterDuet's website, another online scriptwriting service; Scripped had advertised WriterDuet in Scripped's shutdown open letter. == Features == The Scripped Writer provided a built-in screenplay template which formatted the document to a standard for scripts as recommended by the AMPAS. The screenplay document was composed of seven elements: scene, action, character, dialog, parenthetical, transition and general. Each element had a specific style to which the Scripped Writer conformed as text was entered. Like other client-side screenplay software, Scripped offered Tab-Enter toggling between screenplay elements, making the writing process much faster. Text files could be imported into the Scripped Writer and automatically conformed to the screenplay template. Completed scripts could be exported as PDF files. In May 2011 the administrators of Scripped launched Scripted.com - a sister site focused on freelance writing jobs. Subsequent to the service's launch, the company was renamed to Scripted, Inc.
Read more →
GermaNet

GermaNet is a semantic network for the German language. It relates nouns, verbs, and adjectives semantically by grouping lexical units that express the same concept into synsets and by defining semantic relations between these synsets. GermaNet is free for academic use, after signing a license. GermaNet shares much in common with the English WordNet and can be viewed as an online thesaurus or a light-weight ontology. GermaNet has been developed and maintained at the University of Tübingen since 1997 within the research group for General and Computational Linguistics. It has been integrated into the EuroWordNet, a multilingual lexical-semantic database. == Database == === Contents === GermaNet partitions the lexical space into a set of concepts that are interlinked by semantic relations. A semantic concept is modeled by a synset. A synset is a set of words (called lexical units) where all the words are taken to have the same or almost the same meaning. Thus, a synset is a set of synonyms grouped under one definition, or "gloss". In addition to the gloss, synsets are labeled with their syntactic function and accompanied by example sentences for each distinct meaning in the synset. Just as in WordNet, for each word category the semantic space is divided into a number of semantic fields closely related to major nodes in the semantic network: Ort, or "location", Körper, or "body", etc. As of version 20.0 (release November 2025), GermaNet contains: Synsets: 179438 Lexical units: 231500 Literals: 216517 1.29 lexical units per synset Number of conceptual relations: 194367 Number of lexical relations: 13602 (synonymy excluded) Number of split compounds: 130901 Number of Interlingual Index (ILI) records: 28561 Number of Wiktionary sense descriptions: 29539 === Format === All GermaNet data is stored in a PostgreSQL relational database. The database schema follows the internal structure of GermaNet: there are tables to store synsets, lexical units, conceptual and lexical relations, etc. GermaNet data is distributed both in this database format and as XML files. In the XML data, two types of files, one for synsets and the other for relations, represent all data available in the GermaNet database. == Interfaces == There are software libraries and APIs available for Java and Python. These programs are distributed under free-software licenses and provide easy access to all information in various versions of GermaNet. GermaNet Rover is an on-line application that can be used to search for synsets in GermaNet, explore the data associated with them, and calculate the semantic similarity of pairs of synsets. It features visualizations of the hypernym relation and advanced filtering options for synset searching. == Licenses == GermaNet 20.0 (released November 2025) can be distributed under one of the following types of license agreements: Academic Research License Agreement: for the purpose of research at academic institutions. There is no license fee for academic use. Licenses are not given to individual students, and those seeking a license are required to talk to an academic advisor. Research and Development License Agreement: applies to non-academic institutions and research consortia. To be used strictly for technology development and internal research. Commercial License Agreement: applies to non-academic institutions and commercial enterprises. It permits technology development and internal research, as well as giving the non-exclusive right to distribute and market any derived product or service. == Alternatives == Open-de-WordNet is a freely available alternative to GermaNet which is compatible with WordNet. == Linguistic applications == GermaNet has been used for a variety of applications, including: semantic analysis shallow recognition of implicit document structure compound analysis analyzing sectional preferences word sense disambiguation
Read more →
Botler AI

Botler AI is a Montreal-based Canadian Artificial Intelligence company that helps users navigate the legal system. Launched in 2017 by Amir Morv and Ritika Dutt, Botler offers a free online tool which provides users who are unaware of their legal rights with information and guidance. Botler is known for its role in unveiling misconduct in the Government of Canada's procurement practices. Botler's findings have prompted numerous investigations, including by the Royal Canadian Mounted Police. == History == Botler's first AI was trained on over 300,000 U.S. and Canadian legal documents to help individuals identify and enforce their legal rights, without fear of judgment. Launched during the height of the #MeToo movement, the tool initially focused on sexual harassment with a goal of creating "a general artificial intelligence that would help the average person with any legal issue." === Department of Justice Canada === In 2020, Botler launched an expanded misconduct detection system in the form of an anonymous chatbot which provided users with an explanation of the law and relevant resources. In March 2021, the Minister of Justice and Attorney General of Canada announced the Government of Canada's support for Botler AI to assist complainants of sexual harassment in the workplace. The initiative, entitled Botler for Citizens and implemented with the support of the Department of Justice Canada, established an Artificial Intelligence-powered hybrid legal service delivery model. == Notable cases == On October 4, 2023, the RCMP confirmed to The Globe and Mail that they "are investigating a file referred from the CBSA (Canada Border Services Agency) that is based on allegations brought to their attention by Botler". In 2019, GCStrategies's managing partner, Kristian Firth, reached out to Botler on behalf of his client, the CBSA, to solicit their misconduct detection chatbot. After interactions with GCStrategies, Dalian Enterprises and Coradix Technology Consulting, the three main contractors involved in developing the controversial ArriveCAN app, Dutt and Morv alerted the CBSA to questionable contracting practices in federal government procurement in September, 2021, and again in November, 2022. In response to Botler's November 2022 report, the CBSA launched an internal review and referred the matter to the RCMP. During testimony before a parliamentary committee, the CBSA's President stated that the CBSA investigation to date has raised some concerns and shows "that there was a pattern of persistent collaboration between certain officials and GCStrategies... to circumvent or ignore certain established processes and roles and responsibilities". The Auditor General of Canada, which extended its study into ArriveCAN following the Botler revelations, found that GCStrategies was directly involved in setting narrow terms for a request for proposal for a $25-million government contract it ultimately won. The firm, which has just two employees, charges the government a commission of between 15 per cent and 30 per cent of each contract's value. The Office of the Procurement Ombudsman of Canada found "numerous examples" where GCStrategies "had simply copied and pasted" the required work experience to meet contracting requirements. To date, more than a dozen probes have been launched into the matter, including by the government, parliamentary committees, independent watchdogs and law-enforcement agencies. On April 17, 2024, GCStrategies' Firth was the first person summoned in over a century to answer questions before Members of Parliament in the House of Commons. During his appearance, Firth testified that the RCMP had raided "my property to obtain electronic goods surrounding the Botler allegations". === Government of Canada Reforms === One day after The Globe reported that the RCMP is investigating allegations of misconduct, the federal government responded by announcing new guidelines from the Treasury Board of Canada aimed at cutting back on the use of private consultants and that outsourcing contracts were under examination. Public Services and Procurement Canada (PSPC) invalidated and replaced all master level user agreements with government client departments in November 2023. The agreements set out the conditions for access to select Professional Services methods of supply which are used for outsourcing. In March 2024, PSPC announced its suspension of the respective security statuses of GCStrategies, Dalian and Coradix, barring them from participating in all federal procurements. Records show that the total value of contracts awarded to the three companies amounts to more than $1 Billion.
Read more →