AI Art Tool Free

AI Art Tool Free — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Artificial reproduction

  Artificial reproduction is the re-creation of life brought about by means other than natural ones. It is new life built by human plans and projects. Examples include artificial selection, artificial insemination, in vitro fertilization, artificial womb, artificial cloning, and kinematic replication. Artificial reproduction is one aspect of artificial life. Artificial reproduction can be categorized into one of two classes according to its capacity to be self-sufficient: non-assisted reproductive technology and assisted reproductive technology. Cutting plants' stems and placing them in compost is a form of assisted artificial reproduction, xenobots are an example of a more autonomous type of reproduction, while the artificial womb presented in the movie the Matrix illustrates a non assisted hypothetical technology. The idea of artificial reproduction has led to various technologies. == Theology == Humans have aspired to create life since immemorial times. Most theologies and religions have conceived this possibility as exclusive of deities. Christian religions consider the possibility of artificial reproduction, in most cases, as heretical and sinful. == Philosophy == Although ancient Greek philosophy raised the concept that man could imitate the creative capacity of nature, classic Greeks thought that if possible, human beings would reproduce things as nature does, and vice versa, nature would do the things that man does in the same way. Aristotle, for example, wrote that if nature made tables, it would make them just as men do. In other words, Aristotle said that if nature were to create a table, such table will look like a human-made table. Correspondingly, Descartes envisioned the human body, and nature, as a machine. Cartesian philosophy does not stop seeing a perfect mirror between nature and the artificial. However, Kant revolutionized this old idea by criticizing such naturalism. Kant pedagogically wrote: "Reason, in order to be taught by nature, must approach nature with its principles in one hand, according to which the agreement among appearances can count as laws, and, in the other hand, the experiment thought out in accord with these principles—in order to be instructed by nature not like a pupil, who has recited to him whatever the teacher wants to say, but like an appointed judge who compels witnesses to answer the questions he puts to them.". Humans are not instructed by nature but rather use nature as raw material to invent. Humans find alternatives to the natural restrictions imposed by natural laws thus, nature is not necessarily mirrored. In accordance with Kant (and contrary to what Aristotle thought) Karl Marx, Alfred Whitehead, Jaques Derrida and Juan David García Bacca noticed that nature is incapable of reproducing tables; or airplanes, or submarines, or computers. If nature tried to create airplanes, it would produce birds. If nature tried to create submarines, it would get fishes. If nature tried to create computers, brains would grow. And if nature tried to create man, modern man, monkeys will be evolved. According to Whitehead, if we look for something natural in artificial life, in the most elaborate cases, if anything, only atoms remain natural. Juan David Garcia Bacca summarized, “It will not come out from wood, it will not be born, a galley; from clay, a vessel; from linen, a dress; from iron, a lever,...From natural, artificial. In the artificial, the natural is reduced to a simple raw material, even though it is perfectly specified with natural specification. The artificial is the real, positive, and original negation of the natural: of species, of genus and of essence. Thus, its ontology is superior to natural ontology. And for this very reason Marx did not attach any importance to Darwin, whose evolutionism is confined to the natural order: to changes, at most, from variety to variety, from species to species... natural. For the same reason, nature has no dialectics, even though continuous evolution and selection can occur. The dialectic cannot emerge from the natural, for deeper reasons than, using today's terms, from a bird, an airplane cannot emerge; from fish, a submarine; from ears, a telephone; from eyes, a television; from a brain, a digital computer; from feet, a car; from hands, an engine; from Euclid, Descartes; from Aristotle, Newton; from Plato, Marx.” According to García Bacca, the major difference between natural causes and artificial causes is that nature does not have plans and projects, while humans design things following plans and projects. In contrast, other influential authors such as Michael Behe have depicted the concept and promoted the idea of intelligent design, a notion that has aroused several doubts and heated controversies, as it reframe natural causes in accordance with a natural plan. Previous ideas that have also provided a positive 'sense' to natural reproduction, are orthogenesis, syntropy, orgone and morphic resonance, among others. Although, these ideas have been historically marginalized and often called pseudoscience, recently Bio-semioticians are reconsidering some of them under symbolic approaches. Current metaphysics of science actually recognizes that the artificial ways of reproduction are diverse from nature, i.e., unnatural, anti-natural or supernatural. Because Biosemiotics does not focus on the function of life but on its meaning, it has a better understanding of the artificial than classic biology. == Science == Biology, being the study of cellular life, addresses reproduction in terms of growth and cellular division (i.e., binary fission, mitosis and meiosis); however, the science of artificial reproduction is not restricted by the mirroring of these natural processes.The science of artificial reproduction is actually transcending the natural forms, and natural rules, of reproduction. For example, xenobots have redefined the classical conception of reproduction. Although xenobots are made of eukariotic cells they do not reproduce by mitosis, but rather by kinematic replication. Such constructive replication does not involve growing but rather building. == Assisted reproductive technologies == Assisted reproductive technology (ART)'s purpose is to assist the development of a human embryo, commonly because of medical concerns due to fertility limitations. == Non-assisted reproductive technologies == Non-assisted reproductive technologies (NART) could have medical motivations but are mostly driven by a wider heterotopic ambition. Although, NARTs are initially designed by humans, they are programed to become independent of humans to a relative or absolute extent. James Lovelock proposed that such novelties could overcome humans. === Artificial cloning === Cloning is the cellular reproductive processes where two or more genetically identical organisms are created, either by natural or artificial means. Artificial cloning normally involves editing the genetic code, somatic cell nuclear transfer and 3D bioprinting. === Non-assisted artificial womb === A non-assisted artificial womb or artificial uterus is a device that allow for ectogenesis or extracorporeal pregnancy by growing an embryonic form outside the body of an organism (that would normally carry the embryo to term) without any human assistance. The aspect of non-assistance is the key distinction between the current artificial womb technology (AWT) in modern medical research, which still relies on human assistance. With this non-assisted hypothetical technology, a zygote or stem cells are used to create an embryo that is then incubated and monitored by artificial intelligence (AI) within a chamber composed of biocompatible material. The AI maintains the necessary conditions for the embryo to develop and thrive, proceeding to mimic organic labor and childbirth in order to best help the embryo adjust to the outside world. Ectogenesis—gestation, depicted in the science fiction movie The Matrix, is a fast approaching reality. This type of innovation presupposes that vertebrate wombs are not the only way for bearing humans or other similar forms of life. === Kinematic replication === Self-replication without binary fission, meiosis, mitosis (or any other form of cellular reproduction that involves division and growing) can be achieved. Xenobots are an example of kinematic replication. They are biobots, named after the African clawed frog (Xenopus laevis). Xenobots are cellular life forms designed by using artificial intelligence to build more of themselves by combining frog cells in a liquid medium. The term kinematic replication is usually reserved for biomolecules (e.g. DNA, RNA, prions, etc.) and artificially designed cellular forms (e.g. xenobots). === Machine constructive replication === Machine constructive replication mimics human traditional manufacturing but is entirely self-automated. Such constructive replication is a more general form of kinematic replication, which does not necessarily

  Read more →
• 

  Sieve of Pritchard

  In mathematics, the sieve of Pritchard is an algorithm for finding all prime numbers up to a specified bound. Like the ancient sieve of Eratosthenes, it has a simple conceptual basis in number theory. It is especially suited to quick hand computation for small bounds. Whereas the sieve of Eratosthenes marks off each non-prime for each of its prime factors, the sieve of Pritchard avoids considering almost all non-prime numbers by building progressively larger wheels, which represent the pattern of numbers not divisible by any of the primes processed thus far. It thereby achieves a better asymptotic complexity, and was the first sieve with a running time sublinear in the specified bound. Its asymptotic running-time has not been improved on, and it deletes fewer composites than any other known sieve. It was created in 1979 by Paul Pritchard. Since Pritchard has created a number of other sieve algorithms for finding prime numbers, the sieve of Pritchard is sometimes singled out by being called the wheel sieve (by Pritchard himself) or the dynamic wheel sieve. == Overview == A prime number is a natural number that has no natural number divisors other than the number 1 and itself. To find all the prime numbers less than or equal to a given integer N, a sieve algorithm examines a set of candidates in the range 2, 3, …, N, and eliminates those that are not prime, leaving the primes at the end. The sieve of Eratosthenes examines all of the range, first removing all multiples of the first prime 2, then of the next prime 3, and so on. The sieve of Pritchard instead examines a subset of the range consisting of numbers that occur on successive wheels, which represent the pattern of numbers left after each successive prime is processed by the sieve of Eratosthenes. For i > 0, the ith wheel Wi represents this pattern. It is the set of numbers between 1 and the product Pi = p1 · p2 ⋯ pi of the first i prime numbers that are not divisible by any of these prime numbers (and is said to have an associated length Pi). This is because adding Pi to a number does not change whether it is divisible by one of the first i prime numbers, since the remainder on division by any one of these primes is unchanged. So W1 = {1} with length P1 = 2 represents the pattern of odd numbers; W2 = {1,5} with length P2 = 6 represents the pattern of numbers not divisible by 2 or 3; etc. Wheels are so-called because Wi can be usefully visualized as a circle of circumference Pi with its members marked at their corresponding distances from an origin. Then rolling the wheel along the number line marks points corresponding to successive numbers not divisible by one of the first i prime numbers. The animation shows W2 being rolled up to 30. It is useful to define Wi → n for n > 0 to be the result of rolling Wi up to n. Then the animation generates W2 → 30 = {1,5,7,11,13,17,19,23,25,29}. Note that up to 52 − 1 = 24, this consists only of 1 and the primes between 5 and 25. The sieve of Pritchard is derived from the observation that this holds generally: for all i > 0, the values in Wi → (p2i+1 − 1) are 1 and the primes between pi+1 and p2i+1. It even holds for i = 0, where the wheel has length 1 and contains just 1 (representing all the natural numbers). So the sieve of Pritchard starts with the trivial wheel W0 and builds successive wheels until the square of the wheel's first member after 1 is at least N. Wheels grow very quickly, but only their values up to N are needed and generated. It remains to find a method for generating the next wheel. Note in the animation that W3 = {1,5,7,11,13,17,19,23,25,29} − {5 · 1 , 5 · 5} can be obtained by rolling W2 up to 30 and then removing 5 times each member of W2.This also holds generally: for all i ≥ 0, Wi+1 = (Wi → Pi+1) − {pi+1 · w | w ∈ Wi}. Rolling Wi past Pi just adds values to Wi, so the current wheel is first extended by getting each successive member starting with w = 1, adding Pi to it, and inserting the result in the set. Then the multiples of pi+1 are deleted. Care must be taken to avoid a number being deleted that itself needs to be multiplied by pi+1. The sieve of Pritchard as originally presented does so by first skipping past successive members until finding the maximum one needed, and then doing the deletions in reverse order by working back through the set. This is the method used in the first animation above. A simpler approach is just to gather the multiples of pi+1 in a list, and then delete them. Another approach is given by Gries and Misra. If the main loop terminates with a wheel whose length is less than N, it is extended up to N to generate the remaining primes. The algorithm, for finding all primes up to N, is therefore as follows: Start with a set W = {1} and length = 1 representing wheel 0, and prime p = 2. As long as p2 ≤ N, do the following: if length < N, then extend W by repeatedly getting successive members w of W starting with 1 and inserting length + w into W as long as it does not exceed p · length or N; increase length to the minimum of p · length and N. repeatedly delete p times each member of W by first finding the largest ≤ length and then working backwards. note the prime p, then set p to the next member of W after 1 (or 3 if p was 2). if length < N, then extend W to N by repeatedly getting successive members w of W starting with 1 and inserting length + w into W as long as it does not exceed N; On termination, the rest of the primes up to N are the members of W after 1. === Example === To find all the prime numbers less than or equal to 150, proceed as follows. Start with wheel 0 with length 1, representing all natural numbers 1, 2, 3...: 1 The first number after 1 for wheel 0 (when rolled) is 2; note it as a prime. Now form wheel 1 with length 2 × 1 = 2 by first extending wheel 0 up to 2 and then deleting 2 times each number in wheel 0, to get: 1 2 The first number after 1 for wheel 1 (when rolled) is 3; note it as a prime. Now form wheel 2 with length 3 × 2 = 6 by first extending wheel 1 up to 6 and then deleting 3 times each number in wheel 1, to get 1 2 3 5 The first number after 1 for wheel 2 is 5; note it as a prime. Now form wheel 3 with length 5 × 6 = 30 by first extending wheel 2 up to 30 and then deleting 5 times each number in wheel 2 (in reverse order), to get 1 2 3 5 7 11 13 17 19 23 25 29 The first number after 1 for wheel 3 is 7; note it as a prime. Now wheel 4 has length 7 × 30 = 210, so we only extend wheel 3 up to our limit 150. (No further extending will be done now that the limit has been reached.) We then delete 7 times each number in wheel 3 until we exceed our limit 150, to get the elements in wheel 4 up to 150: 1 2 3 5 7 11 13 17 19 23 25 29 31 37 41 43 47 49 53 59 61 67 71 73 77 79 83 89 91 97 101 103 107 109 113 119 121 127 131 133 137 139 143 149 The first number after 1 for this partial wheel 4 is 11; note it as a prime. Since we have finished with rolling, we delete 11 times each number in the partial wheel 4 until we exceed our limit 150, to get the elements in wheel 5 up to 150: 1 2 3 5 7 11 13 17 19 23 25 29 31 37 41 43 47 49 53 59 61 67 71 73 77 79 83 89 91 97 101 103 107 109 113 119 121 127 131 133 137 139 143 149 The first number after 1 for this partial wheel 5 is 13. Since 13 squared is at least our limit 150, we stop. The remaining numbers (other than 1) are the rest of the primes up to our limit 150. Just 8 composite numbers are removed, once each. The rest of the numbers considered (other than 1) are prime. In comparison, the natural version of Eratosthenes sieve (stopping at the same point) removes composite numbers 184 times. == Pseudocode == The sieve of Pritchard can be expressed in pseudocode, as follows: algorithm Sieve of Pritchard is input: an integer N >= 2. output: the set of prime numbers in {1,2,...,N}. let W and Pr be sets of integer values, and all other variables integer values. k, W, length, p, Pr := 1, {1}, 2, 3, {2}; {invariant: p = pk+1 and W = Wk ∩ {\displaystyle \cap } {1,2,...,N} and length = minimum of Pk,N and Pr = the primes up to pk} while p2 <= N do if (length < N) then Extend W,length to minimum of plength,N; Delete multiples of p from W; Insert p into Pr; k, p := k+1, next(W, 1) if (length < N) then Extend W,length to N; return Pr ∪ {\displaystyle \cup } W - {1}; where next(W, w) is the next value in the ordered set W after w. procedure Extend W,length to n is {in: W = Wk and length = Pk and n > length} {out: W = Wk → {\displaystyle \rightarrow } n and length = n} integer w, x; w, x := 1, length+1; while x <= n do Insert x into W; w := next(W,w); x := length + w; length := n; procedure Delete multiples of p from W,length is integer w; w := p; while pw <= length do w := next(W,w); while w > 1 do w := prev(W,w); Remove pw from W; where prev(W, w) is the previous value in the ordered set W before w. The algorithm can be initialized with W0 instead of W1 at the minor complication of making next(W, 1) a special case when k = 0. This a

  Read more →
• 

  Enterprise data planning

  Enterprise data planning is the starting point for enterprise wide change. It states the destination and describes how you will get there. It defines benefits, costs and potential risks. It provides measures to be used along the way to judge progress and adjust the journey according to changing circumstances. Data is fundamental to investment enterprises. Effective, economic management of data underpins operations and enables transformations needed to satisfy customer demands, competition and regulation. Data warehouse(s) and other aspects of the overall data architecture are critical to the enterprise. EDMworks has created a strategic data planning approach for the Investment Sector. It consists of a planning process, planning intranets, templates and training materials. EDMworks planning process is based on the belief that extensive domain knowledge significantly shortens planning iterations and enables progressively higher quality plans to be produced and implemented. This approach drives the development of an effective and economic enterprise data architecture. Enterprise data planning is based on proven business disciplines. Key architectural layers for data and applications are then added in order to provide an enterprise wide understanding of the uses and interdependencies of data. This enables the definition of the core components of the EDM plan: Industry structure and business objectives Assessment of systems and services Target architecture for applications, data and infrastructure Target organization structures Systems, database, infrastructure and organizational plans Business case, costs, benefits, results and risks. EDMworks uses several components from the Open Systems Group TOGAF enterprise systems planning process. TOGAF acts as an extension to good business planning methods to provide a framework for the development of the systems and data architectural components. == History == James Martin was one of the pathfinders in data planning methodologies. He was one of the first to identify data as being an enterprise wide asset that required management. He developed a series of tools and methods to support that process. Most of the large consulting firms developed their own methods to address the same basic issue. Frequently, their approaches were incorporated into their own branded system development methodologies that encompassed the complete systems development life-cycle. Others, such as Ed Tozer, developed more focused offerings that dealt with the complexities of extracting key business needs from senior management and then defining relevant architectural visions for the specific enterprise. From these various sources, the concepts of Business, Data, Applications and Technology Architectures emerged. The Open Group Architectural Framework (TOGAF) has taken this work forward and has established a sound method in TOGAF version 9. EDMworks approach is to adopt these planning and architectural practices as a basis and then add two additional dimensions to the planning and implementation focus: Domain knowledge of the Investments sector. Investments is a complex global industry with a common set of characteristics about clients, information vendors, competition and regulation. Domain knowledge significantly improves the quality of the planning and implementation processes Development of people and teams. Change is a major feature of in any Enterprise Data Management program and people and teams both need development in order to make EDM effective throughout an organization.

  Read more →
• 

  Archetype (information science)

  In the field of informatics, an archetype is a formal re-usable model of a domain concept. Traditionally, the term archetype is used in psychology to mean an idealized model of a person, personality or behaviour (see Archetype). The usage of the term in informatics is derived from this traditional meaning, but applied to domain modelling instead. An archetype is defined by the OpenEHR Foundation (for health informatics) as follows: An archetype is a computable expression of a domain content model in the form of structured constraint statements, based on some reference model. openEHR archetypes are based on the openEHR reference model. Archetypes are all expressed in the same formalism. In general, they are defined for wide re-use, however, they can be specialized to include local particularities. They can accommodate any number of natural languages and terminologies. == Formal specifications == The modern archetype formalism is specified and maintained by the openEHR Foundation, and although originally developed for the health IT domain, is completely domain-independent, and has been used in geospatial modelling, telecommunications, and defence. The archetype formalism consists of a number of specifications including: 'ADL 1.4': original release of Archetype Definition Language (ADL) and Archetype Object Model (AOM); widely implemented in health IT domain; 'ADL 2': modern release of Archetype Definition Language (ADL), Archetype Object Model (AOM), Archetype Identification specification and Archetype Technology Overview. The Archetype Technology Overview provides a short technical overview of the archetype formalism useful for new users. The ADL/AOM 1.4 specifications were provided to ISO TC 215 in 2008 by the openEHR Foundation and became the ISO 13606-2 standard, extant until 2019. ISO TC 215 accepted the AOM 2 specification as the basis for a revision of this standard, which was issued in 2019. In late 2015, the Object Management Group (OMG) accepted an RfP entitled 'Archetype Modeling Language (AML)' as a new candidate standard. This specification is a form of ADL re-engineered as a UML profile so as to enable archetype modelling to be supported within UML tools. == Tools == A number of tools area available for working with archetypes. Most are listed on the openEHR modelling tools page. They include: ADL Designer, a modern AOM2-based web editing application Archetype Editor, an original desktop clinical modelling tool Template Designer, an original desktop clinical templating tool LinkEHR, an archetype and data integration tool ADL Workbench, reference compiler and visualiser tool == Example ==

  Read more →
• 

  StatMuse

  StatMuse Inc. is an American artificial intelligence company founded in 2014. It operates an eponymous website that hosts a database of sports statistics covering the four major North American sports leagues, the Women's National Basketball Association (WNBA), NCAA Division I men's basketball, NCAA Division I Football Bowl Subdivision, the Big Five association football leagues in Europe, and various professional golf tours. == History == The company was founded by friends Adam Elmore and Eli Dawson in 2014. In email correspondence to the Springfield News-Leader, Elmore detailed that he and Dawson, fans of the National Basketball Association (NBA), were compelled to create StatMuse after they realized there was no online platform where they could search "Lebron James most points" [sic] and quickly get a result "showing his highest scoring games." As a startup, the company's goal was to utilize a type of artificial intelligence called natural language processing (NLP) for sports. In 2015, the company was part of the second group of startups accepted into the Disney Accelerator program. The company secured support from several investors, including The Walt Disney Company, Techstars, Allen & Company, the NFL Players Association, Greycroft and NBA Commissioner David Stern. As part of their partnership with Disney, StatMuse signed a content deal with ESPN (owned by Disney) to provide stats content on social media and television during the 2015–16 NBA season. Initially, the company only had stats available for the NBA, but eventually expanded to provide stats for the other major North American sports leagues. The company's initial demographic was players of fantasy sports, but it eventually expanded to target general sports fans as well. StatMuse offers responses to user queries in the voices of sports-related public figures. Dawson shared with VentureBeat that StatMuse brings people in and records them saying different words and phrases. These celebrity voices were made accessible through Google's Google Assistant service, Microsoft's Cortana virtual assistant, and Amazon's Echo devices. The company launched its phone app in September 2017. The app allows users to access StatMuse's sports statistics database by submitting queries in their natural language. Upon the launch of the phone app, Fitz Tepper of TechCrunch wrote that: "The technology isn't perfect – some of the pauses between words are a bit awkward, making it clear that some phrases are being stitched together on the fly. But this is the exception, and on the whole, most responses sound pretty good." StatMuse plug-ins for Slack and Facebook Messenger were also made, providing text-based sports stats. In 2019, StatMuse received investment from the Google Assistant Investment program. The service launched a premium option dubbed StatMuse+ in May 2023, offering options that had previously been included for free, such as unlimited searches and full results in data tables. The premium version also included early access to new features and a personalized search history, as well as not having ads. The app received a variety of feedback. In January 2024, the service launched a Premier League version of the website dubbed StatMuse FC. It is planned to introduce more leagues on the website.

  Read more →
• 

  TurboQuant

  TurboQuant is an online vector quantization algorithm for compressing high-dimensional Euclidean vectors while preserving their geometric structure. It was proposed in 2025 by Amir Zandieh, Majid Daliri, Majid Hadian, and Vahab Mirrokni in the paper TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate. The paper lists Zandieh and Mirrokni as affiliated with Google Research, Daliri with New York University, and Hadian with Google DeepMind. The method was developed for applications including large language model (LLM) inference, key–value (KV) cache compression, vector databases, and nearest neighbor search. TurboQuant consists of two related algorithms: TurboQuantmse, which is optimized for mean squared error (MSE), and TurboQuantprod, which is optimized for unbiased inner product estimation. The algorithm uses a random rotation of input vectors, applies scalar quantizers to the rotated coordinates, and, for inner-product estimation, applies a one-bit Quantized Johnson–Lindenstrauss (QJL) transform to the residual error. == Background == Vector quantization is a compression method that maps high-dimensional vectors to a finite set of codewords. The problem has roots in Shannon's source coding theory and rate–distortion theory. In machine learning and information retrieval, vector quantization is used to reduce the memory required to store embeddings, activation vectors, and other numerical representations. In Transformer-based large language models, the KV cache stores key and value vectors from previous tokens during autoregressive decoding. The size of this cache grows with context length, the number of attention heads, and the number of concurrent requests, making it a major memory bottleneck in LLM serving. Similar compression problems appear in vector search, where large collections of embedding vectors must be stored and searched efficiently. Earlier approaches to vector quantization include product quantization, scalar quantization, and data-dependent k-means codebook construction. The TurboQuant paper argues that many existing methods either require offline preprocessing and calibration or suffer from suboptimal distortion guarantees in online settings. == Algorithm == === TurboQuantmse === TurboQuantmse is the version of the algorithm optimized for mean-squared error. For a unit vector x ∈ S d − 1 {\displaystyle x\in S^{d-1}} , the algorithm first applies a random rotation matrix Π ∈ R d × d {\displaystyle \Pi \in \mathbb {R} ^{d\times d}} and sets z = Π x {\displaystyle z=\Pi x} . Each coordinate of the rotated vector follows a shifted and scaled beta distribution, which converges to a normal distribution in high dimensions. In high dimensions, distinct coordinates also become nearly independent, allowing the algorithm to apply scalar quantizers independently to each coordinate. The scalar quantizer is constructed by solving a one-dimensional continuous k-means or Lloyd–Max quantization problem. If the centroids are c 1 , c 2 , … , c 2 b {\displaystyle c_{1},c_{2},\ldots ,c_{2^{b}}} , the quantization step stores, for each coordinate, i d x j = ⁡ a r g m i n k ∈ [ 2 b ] | z j − c k | . {\displaystyle \mathrm {idx} _{j}=\operatorname {} {arg\,min}_{k\in [2^{b}]}|z_{j}-c_{k}|.} During dequantization, the stored index for each coordinate is replaced by the corresponding centroid, giving a reconstructed rotated vector z ~ {\displaystyle {\tilde {z}}} . The algorithm then rotates back: x ~ = Π ⊤ z ~ . {\displaystyle {\tilde {x}}=\Pi ^{\top }{\tilde {z}}.} The paper gives the following bound for TurboQuantmse: D m s e ≤ 3 π 2 ⋅ 1 4 b . {\displaystyle D_{\mathrm {mse} }\leq {\frac {\sqrt {3\pi }}{2}}\cdot {\frac {1}{4^{b}}}.} It also reports finer-grained MSE values of approximately 0.36, 0.117, 0.03, and 0.009 for bit-widths b = 1 , 2 , 3 , 4 {\displaystyle b=1,2,3,4} , respectively. === TurboQuantprod === TurboQuantprod is optimized for unbiased inner-product estimation. The authors note that an MSE-optimized quantizer may introduce bias when used to estimate inner products. To address this, TurboQuantprod first applies TurboQuantmse with bit-width b − 1 {\displaystyle b-1} , then applies a one-bit Quantized Johnson–Lindenstrauss transform to the remaining residual vector. Let r = x − Q m s e − 1 ( Q m s e ( x ) ) {\displaystyle r=x-Q_{\mathrm {mse} }^{-1}(Q_{\mathrm {mse} }(x))} be the residual after MSE quantization, and let γ = ‖ r ‖ 2 {\displaystyle \gamma =\|r\|_{2}} . The QJL step stores a sign vector for the residual. For γ ≠ 0 {\displaystyle \gamma \neq 0} , this can be written using the normalized residual u = r / γ {\displaystyle u=r/\gamma } : q j l = sign ⁡ ( S u ) , {\displaystyle qjl=\operatorname {sign} (Su),} where S ∈ R d × d {\displaystyle S\in \mathbb {R} ^{d\times d}} is a random projection matrix. Since the sign function is invariant under positive rescaling, this is equivalent to sign ⁡ ( S r ) {\displaystyle \operatorname {sign} (Sr)} when r ≠ 0 {\displaystyle r\neq 0} . If γ = 0 {\displaystyle \gamma =0} , the residual correction is zero. TurboQuantprod stores the MSE quantization, the QJL sign vector, and the residual norm: Q p r o d ( x ) = [ Q m s e ( x ) , q j l , γ ] . {\displaystyle Q_{\mathrm {prod} }(x)=\left[Q_{\mathrm {mse} }(x),qjl,\gamma \right].} The dequantized vector is reconstructed as x ~ = x ~ m s e + π / 2 d γ S ⊤ q j l . {\displaystyle {\tilde {x}}={\tilde {x}}_{\mathrm {mse} }+{\frac {\sqrt {\pi /2}}{d}}\,\gamma S^{\top }qjl.} The paper proves that TurboQuantprod is unbiased for inner-product estimation: E x ~ [ ⟨ y , x ~ ⟩ ] = ⟨ y , x ⟩ . {\displaystyle \mathbb {E} _{\tilde {x}}\left[\langle y,{\tilde {x}}\rangle \right]=\langle y,x\rangle .} It also gives the distortion bound D p r o d ≤ 3 π 2 ⋅ ‖ y ‖ 2 2 d ⋅ 1 4 b . {\displaystyle D_{\mathrm {prod} }\leq {\frac {\sqrt {3\pi }}{2}}\cdot {\frac {\|y\|_{2}^{2}}{d}}\cdot {\frac {1}{4^{b}}}.} == Performance and applications == The TurboQuant paper reports that the algorithm achieves near-optimal distortion rates within a small constant factor of information-theoretic lower bounds. The authors report that, for KV cache quantization, TurboQuant achieved quality neutrality at 3.5 bits per channel and marginal degradation at 2.5 bits per channel. In long-context LLM experiments using Llama 3.1 8B Instruct, the paper evaluated the method on a "needle-in-a-haystack" retrieval task with document lengths from 4,000 to 104,000 tokens. It reported that TurboQuant matched the uncompressed full-precision baseline while using more than 4× compression, and compared the method against PolarQuant, SnapKV, PyramidKV, and KIVI. Google Research stated that TurboQuant was evaluated on long-context benchmarks including LongBench, Needle in a Haystack, ZeroSCROLLS, RULER, and L-Eval using open-source models including Gemma and Mistral. According to a report in Tom's Hardware, Google described the method as reducing KV-cache memory by at least six times and achieving up to an eightfold improvement in attention-logit computation on Nvidia H100 GPUs compared with unquantized 32-bit keys. TurboQuant has also been applied to nearest-neighbor vector search. The original paper reports experiments on DBpedia entity embeddings and GloVe embeddings, comparing TurboQuant with product quantization and other vector-search quantization baselines. == Relationship to other methods == TurboQuant is related to several methods for efficient large language model inference and high-dimensional search: Product quantization – a vector quantization technique widely used for approximate nearest-neighbor search Quantization (machine learning) – reducing the numerical precision of weights, activations, or cached tensors in machine learning models PagedAttention – a memory-management algorithm for LLM serving that reduces fragmentation in the KV cache Johnson–Lindenstrauss lemma – a result in high-dimensional geometry used in random projection methods Lloyd's algorithm – an algorithm for scalar and vector quantization, including k-means-style codebook construction Unlike PagedAttention, which focuses on memory allocation and cache layout, TurboQuant reduces the numerical storage cost of the vectors themselves. Unlike many product-quantization methods, TurboQuant is designed to be data-oblivious and online, avoiding dataset-specific codebook training. == Limitations == The strongest performance claims for TurboQuant come from the original paper and Google Research's own publication. Coverage in technology media has noted that the broader impact of the method will depend on real-world implementation details, workloads, and hardware architectures.

  Read more →
• 

  Artificial intelligence in Brazilian industry

  In 2022, 16.9% (1,620) of the 9,586 Brazilian industrial companies with 100 or more employees used artificial intelligence in their operations Among the companies that used AI, the areas of administration (73.8%), product project development (65.9%), processes, services and marketing (65.1%) were those that used it the most, followed by the areas of production (56.4%) and logistics (48.4%). == Current scenario == === Adoption in Brazilian industrial sectors === In senior management, the majority (56%) of executives have a long-term vision for its use. The study also shows that IT, Innovation, and Marketing are the areas where AI use is most widespread, and that 43% of companies are developing or adapting the algorithms they use. The majority of large institutions that reported some type of AI use purchased these solutions from other companies (76%). Some factors for the adoption of artificial intelligence in companies include the establishment of an autonomous strategy by the company (87.0%), and the influence of suppliers and/or customers (63.0%) and the main difficulties in using technologies were high costs (80.8%), lack of qualified personnel in the company (54.6%) and excessive economic risks (49.5%). Three variables are considered the most relevant to explain the option to use AI: the implementation of a digital security policy, the size of companies with 250 or more employees and the characteristics of the company related to information and communication. When analyzing AI use by company size in Brazil, large companies have the highest proportion of AI use, mainly due to their investment capacity and technology experimentation. However, when comparing Brazil and Europe, indicators show an acceleration in AI use among large European companies, while in Brazil the situation remains stable. In 2023, 30% of large companies in the European bloc used some type of AI, a figure that rose to 41% in 2024, while in Brazil these proportions were 41% in 2023 and 38% in 2024. === Workforce === The challenge of upskilling begins with employees who are capable of understanding recent technological changes. Similarly, companies must create the environment and conditions for workforce development conducive to innovation, and universities must be prepared to provide knowledge aligned with the transition process, which in turn must be supported by public policies. The concern with training a specialized workforce in AI can be seen in the low number of graduates and PhDs in computer science and computer engineering in Brazil, compared to the number shown in other countries. As recorded in the document Recommendations for the Advancement of Artificial Intelligence in Brazil, 2019 data from the Coordination for the Improvement of Higher Education Personnel (CAPES) indicate that "the number of PhDs graduated annually in computing remained below 400 in 2016, and is not expected to have increased during the Covid-19 pandemic" (ABC, 2023). In the United States, by contrast, the number of PhDs graduated in these two areas has remained around 1,800 for the past 11 years, and during this period, the number of PhDs specializing in AI jumped from 10% to 19%. Based on data from the CNPq Lattes Platform (October 2019), it is possible to observe that the number of professionals in the AI field in Brazil is 4,429 specialists. This is still a small number compared to the 415,166 IT jobs in the country's business sector alone. === R&D, scientific production and integration with industry === China and the United States lead in the number of publications. These two countries are followed by the G7 members: India, Austria, South Korea, and Spain. Brazil appears in the next group, alongside the Netherlands, Russia, Indonesia, and Ireland. Regarding the promotion of research and technologies related to AI, public entities such as the Coordination for the Improvement of Higher Education Personnel (Capes) and the National Council for Scientific and Technological Development (CNPq) stood out as the main funders. Currently, different countries and territories have been promoting the development of Artificial Intelligence (AI). In the Brazilian case, one of the main initiatives is the creation of Engineering Research Centers/Applied Research Centers (CPE/CPA) in AI by the São Paulo Research Foundation (FAPESP), in collaboration with the Ministry of Science, Technology and Innovation (MCTI), the Ministry of Communications (MC) and the Brazilian Internet Steering Committee (CGI.br). In terms of the number of patents filed and the volume of investments, the leading nations in AI are the United States, China, France, Germany, the United Kingdom, Russia, India, Switzerland, Japan, South Korea, the Netherlands, Sweden, Finland, Ireland, Singapore, Canada, Israel, and Italy. Brazil appears among the top twenty countries in some rankings, mainly due to its good number of publications (approximately 10% of the number of articles published by the United States). The US is home to approximately 60% of the world's top AI researchers, followed by China (11%), Europe (10%), and Canada (6%). To change this scenario, in August 2024, the Brazilian government announced an investment of R$23 billion until 2028 in artificial intelligence, seeking to “transform the country into a global reference in innovation”. == Future challenges == The Organization for Economic Cooperation and Development (2020) report highlighted three factors that hinder the digital transformation journey and application of AI in Brazil: insufficient infrastructure, high costs due to the tax system, and financial limitations, such as limited access to financing. The costs of adopting technology, its incompatibility with the business, and the lack of training also represent obstacles that Brazilian industry must overcome. There are also inherent obstacles for companies. A McKinsey review emphasizes that once a company chooses one or more sectors to focus on, it must select specific applications. Buyers aren't interested in artificial intelligence simply because it's a breakthrough technology; they want AI to generate a good return on investment, whether by solving specific problems, saving money, or increasing sales. If an AI vendor tried to offer a horizontal solution, the value proposition might not be as compelling. Part of the solution to Brazil's technological backwardness involves building an ecosystem fueled by private institutions, universities, and governments.

  Read more →
• 

  Applied Information Science in Economics

  The Applied Information Science in Economics (Russian: Прикладная информатика в Экономике) or Applied Computer Science in Economics is a professional qualification generally awarded in Russian Federation. The degree inherited from the U.S.S.R. education system also known as Specialist degree. The degree is awarded after five years of full-time study and includes several internships, course-works, thesis writing and defense. The degree has similarities with German Magister Artium or Diplom degree. However, due to the Bologna Process number of such degrees are declining. Degree focuses on applying mathematical methods in economics involving maximum information technology. It is very close to applied mathematics, but includes also major part of computer science. == List of specialty codes in the education system == 080801 - Applied computer science in economics 351400 - Applied computer science == Fields of activity == Organization and management; Project design; Experimental research; Marketing; Consulting; Operational and Maintenance. == Major == Information Science and Programming. High Level Methods of Information Science and Programming. Information Technologies in Economics. Computer Systems, Networks and Telecommunications Services. Operational Environments, Systems and Shells. Architecture and Design of Information Systems for Companies. Data Bases. Information security. Information Management. Imitative Simulation.

  Read more →
• 

  Structural risk minimization

  Structural risk minimization (SRM) is an inductive principle of use in machine learning. Commonly in machine learning, a generalized model must be selected from a finite data set, with the consequent problem of overfitting – the model becoming too strongly tailored to the particularities of the training set and generalizing poorly to new data. The SRM principle addresses this problem by balancing the model's complexity against its success at fitting the training data. This principle was first set out in a 1974 book by Vladimir Vapnik and Alexey Chervonenkis and uses the VC dimension. In practical terms, Structural Risk Minimization is implemented by minimizing E t r a i n + β H ( W ) {\displaystyle E_{train}+\beta H(W)} , where E t r a i n {\displaystyle E_{train}} is the train error, the function H ( W ) {\displaystyle H(W)} is called a regularization function, and β {\displaystyle \beta } is a constant. H ( W ) {\displaystyle H(W)} is chosen such that it takes large values on parameters W {\displaystyle W} that belong to high-capacity subsets of the parameter space. Minimizing H ( W ) {\displaystyle H(W)} in effect limits the capacity of the accessible subsets of the parameter space, thereby controlling the trade-off between minimizing the training error and minimizing the expected gap between the training error and test error. The SRM problem can be formulated in terms of data. Given n data points consisting of data x and labels y, the objective J ( θ ) {\displaystyle J(\theta )} is often expressed in the following manner: J ( θ ) = 1 2 n ∑ i = 1 n ( h θ ( x i ) − y i ) 2 + λ 2 ∑ j = 1 d θ j 2 {\displaystyle J(\theta )={\frac {1}{2n}}\sum _{i=1}^{n}(h_{\theta }(x^{i})-y^{i})^{2}+{\frac {\lambda }{2}}\sum _{j=1}^{d}\theta _{j}^{2}} The first term is the mean squared error (MSE) term between the value of the learned model, h θ {\displaystyle h_{\theta }} , and the given labels y {\displaystyle y} . This term is the training error, E t r a i n {\displaystyle E_{train}} , that was discussed earlier. The second term, places a prior over the weights, to favor sparsity and penalize larger weights. The trade-off coefficient, λ {\displaystyle \lambda } , is a hyperparameter that places more or less importance on the regularization term. Larger λ {\displaystyle \lambda } encourages sparser weights at the expense of a more optimal MSE, and smaller λ {\displaystyle \lambda } relaxes regularization allowing the model to fit to data. Note that as λ → ∞ {\displaystyle \lambda \to \infty } the weights become zero, and as λ → 0 {\displaystyle \lambda \to 0} , the model typically suffers from overfitting.

  Read more →
• 

  Operational data store

  An operational data store (ODS) is used for operational reporting and as a source of data for the enterprise data warehouse (EDW). It is a complementary element to an EDW in a decision support environment, and is used for operational reporting, controls, and decision making, as opposed to the EDW, which is used for tactical and strategic decision support. An ODS is a database designed to integrate data from multiple sources for additional operations on the data, for reporting, controls and operational decision support. Unlike a production master data store, the data is not passed back to operational systems. It may be passed for further operations and to the data warehouse for reporting. An ODS should not be confused with an enterprise data hub (EDH). An operational data store will take transactional data from one or more production systems and loosely integrate it, in some respects it is still subject oriented, integrated and time variant, but without the volatility constraints. This integration is mainly achieved through the use of EDW structures and content. An ODS is not an intrinsic part of an EDH solution, although an EDH may be used to subsume some of the processing performed by an ODS and the EDW. An EDH is a broker of data. An ODS is certainly not. Because the data originates from multiple sources, the integration often involves cleaning, resolving redundancy and checking against business rules for integrity. An ODS is usually designed to contain low-level or atomic (indivisible) data (such as transactions and prices) with limited history that is captured "real time" or "near real time" as opposed to the much greater volumes of data stored in the data warehouse generally on a less-frequent basis. == General use == The general purpose of an ODS is to integrate data from disparate source systems in a single structure, using data integration technologies like data virtualization, data federation, or extract, transform, and load (ETL). This will allow operational access to the data for operational reporting, master data or reference data management. An ODS is not a replacement or substitute for a data warehouse or for a data hub but in turn could become a source.

  Read more →
• 

  Artificial intelligence in Indonesia

  Artificial intelligence in Indonesia refers to development, use and governance of artificial intelligence in Indonesia. Indonesia has treated AI as a national policy area through the Strategi Nasional Kecerdasan Artifisial or National Artificial Intelligence Strategy for 2020–2045. Public discussion has focused on the role of AI in sectors such as health, agriculture, education, mobile technology and e-commerce. Recent developments include AI ethics guidance issued by the communications ministry. Proposals for a national AI roadmap and sovereign AI fund, investment in cloud and AI infrastructure, and local-language AI initiatives for Bahasa Indonesia and regional Indonesian languages. == National strategy == Indonesia's National Artificial Intelligence Strategy is known in Indonesian as Strategi Nasional Kecerdasan Artifisial or Stranas KA. The strategy was published as a long-term framework for the development and use of AI between 2020 and 2045. It is intended to guide ministries, government agencies, regional governments and other stakeholders. The strategy identifies five priority sectors: health services, bureaucratic reform, education and research, food security, and mobility and smart cities. OECD lists the Ministry of Research and Technology and the National Research and Innovation Agency as organisations associated with the strategy. The strategy was developed through consultation with public and private stakeholders. == Institutions == The Indonesian Artificial Intelligence Industry Research and Innovation Collaboration, known as KORIKA is the nodal agency for the national AI strategy. KORIKA describes its vision as creating a collaborative ecosystem to accelerate implementation of the national AI strategy towards Vision Indonesia 2045. The Ministry of Communication and Digital Affairs has also been involved in AI governance, digital policy and public communication. In 2025, Reuters reported that the ministry was preparing a national AI roadmap to give investors and developers a clearer view of Indonesia's market, infrastructure and computing capacity. == AI Governance == Indonesia has introduced policy guidance on the ethical use of artificial intelligence. The policy sets out ethical values for the development and use of AI. These include humanity, security, transparency, credibility and accountability, personal data protection, sustainable development and intellectual property protection. A UNESCO country profile on Indonesia noted that Indonesia had adopted a national AI strategy and had policy frameworks. It also identified gaps in internet access, gender inclusion, language datasets, digital talent and cybersecurity. UNESCO recommended that Indonesia update its AI standards, invest in ethical AI, strengthen research coordination and consider establishing a national agency for artificial intelligence. In May 2026, Antara News reported comments by Deputy Minister of Communication and Digital Affairs Nezar Patria. Who said that AI safety requires partnerships, shared standards and continuing dialogue. == Sectors == AI policy discussions in Indonesia have identified health, agriculture, education, government services, mobility and smart cities as areas where AI could be applied. Mobile technology and e-commerce have been discussed as important areas of AI adoption in Indonesia. Research on AI adoption in Indonesia by Siddhartha Paul Tiwari and Adi Fahrudin has also examined mobile and e-commerce sectors. UNESCO has also noted that Indonesia's large digital economy and startup ecosystem have supported AI adoption, while also pointing to challenges in talent, research capacity and cybersecurity. Indonesia is one of the developing-country markets attracting AI infrastructure investment, including data centres. == Challenges == Indonesia faces several challenges in developing and governing AI. These include gaps in computing infrastructure, uneven connectivity outside major cities, shortages of skilled workers, limited research funding, cybersecurity risks, misinformation, data leaks and the underrepresentation of Indonesian and indigenous languages in AI datasets. UNESCO noted that Bahasa is spoken by around 200 million people but remains underrepresented in AI. It also noted that Indonesia has more than 700 indigenous languages, many of which face the risk of extinction. UNESCO recommended stronger coordination in AI research and a more unified strategy for using AI in language preservation.

  Read more →
• 

  Bisection (software engineering)

  Bisection is a method used in software development to identify change sets that result in a specific behavior change. It is mostly employed for finding the patch that introduced a bug. Another application area is finding the patch that indirectly fixed a bug. == Overview == The process of locating the changeset that introduced a specific regression was described as "source change isolation" in 1997 by Brian Ness and Viet Ngo of Cray Research. Regression testing was performed on Cray's compilers in editions comprising one or more changesets. Editions with known regressions could not be validated until developers addressed the problem. Source change isolation narrowed the cause to a single changeset that could then be excluded from editions, unblocking them with respect to this problem, while the author of the change worked on a fix. Ness and Ngo outlined linear search and binary search methods of performing this isolation. Code bisection has the goal of minimizing the effort to find a specific change set. It employs a divide and conquer algorithm that depends on having access to the code history which is usually preserved by revision control in a code repository. == Bisection method == === Code bisection algorithm === Code history has the structure of a directed acyclic graph which can be topologically sorted. This makes it possible to use a divide and conquer search algorithm which: splits up the search space of candidate revisions tests for the behavior in question reduces the search space depending on the test result re-iterates the steps above until a range with at most one bisectable patch candidate remains === Algorithmic complexity === Bisection is in LSPACE having an algorithmic complexity of O ( log ⁡ N ) {\displaystyle O(\log N)} with N {\displaystyle N} denoting the number of revisions in the search space, and is similar to a binary search. === Desirable repository properties === For code bisection it is desirable that each revision in the search space can be built and tested independently. === Monotonicity === For the bisection algorithm to identify a single changeset which caused the behavior being tested to change, the behavior must change monotonically across the search space. For a Boolean function such as a pass/fail test, this means that it only changes once across all changesets between the start and end of the search space. If there are multiple changesets across the search space where the behavior being tested changes between false and true, then the bisection algorithm will find one of them, but it will not necessarily be the root cause of the change in behavior between the start and the end of the search space. The root cause could be a different changeset, or a combination of two or more changesets across the search space. To help deal with this problem, automated tools allow specific changesets to be ignored during a bisection search. == Automation support == Although the bisection method can be completed manually, one of its main advantages is that it can be easily automated. It can thus fit into existing test automation processes: failures in exhaustive automated regression tests can trigger automated bisection to localize faults. Ness and Ngo focused on its potential in Cray's continuous delivery-style environment in which the automatically isolated bad changeset could be automatically excluded from builds. The revision control systems Fossil, Git and Mercurial have built-in functionality for code bisection. The user can start a bisection session with a specified range of revisions from which the revision control system proposes a revision to test, the user tells the system whether the revision tested as "good" or "bad", and the process repeats until the specific "bad" revision has been identified. Other revision control systems, such as Bazaar or Subversion, support bisection through plugins or external scripts. Phoronix Test Suite can do bisection automatically to find performance regressions.

  Read more →
• 

  Prompt engineering

  Prompt engineering is the process of structuring natural language inputs (known as prompts) to produce specified outputs from a generative artificial intelligence (GenAI) model. Context engineering is the related area of software engineering that focuses on the management of non-prompt contexts supplied to the GenAI model, such as metadata, API tools, and tokens. It can also be defined as the practice of designing and refining input instructions given to a generative AI model to produce more accurate, relevant, or useful outputs. Effective prompt engineering involves understanding how a model interprets language, and may include techniques such as few-shot prompting, chain-of-thought prompting, and role assignment. It is increasingly considered a skill for working with large language models (LLMs) in both research and professional contexts. During the 2020s AI boom, prompt engineering became regarded as a business capability across corporations and industries. Employees with the title prompt engineer were hired to create prompts that would increase productivity and efficacy, although the individual title has since lost traction amid AI models that produce better prompts than humans and corporate training in prompting for general employees. Common prompting techniques include multi-shot, chain-of-thought, and tree-of-thought prompting, as well as the use of assigning roles to the model. Automated prompt generation methods, such as retrieval-augmented generation (RAG), provide for greater accuracy and a wider scope of functions for prompt engineers. Prompt injection is a type of cybersecurity attack that targets machine learning models through malicious prompts. == Terminology == The Oxford English Dictionary defines prompt engineering as "The action or process of formulating and refining prompts for an artificial intelligence program, algorithm, etc., in order to optimize its output or to achieve a desired outcome; the discipline or profession concerned with this." In 2023, prompt ("an instruction given to an artificial intelligence program, algorithm, etc., which determines or influences the content it generates") was the runner-up to Oxford's word of the year. === Prompt === A prompt is some natural language text that describes and prescribes the task that an artificial intelligence (AI) should perform. A prompt for a text-to-text language model can be a query, a command, or a longer statement referencing context, instructions, and conversation history. The process of prompt engineering may involve designing clear queries, refining wording, providing relevant context, specifying the style of output, and assigning a character for the AI to mimic in order to guide the model toward more accurate, useful, and consistent responses. When communicating with a text-to-image or a text-to-audio model, a typical prompt contains a description of a desired output such as "a high-quality photo of an astronaut riding a horse" or "Lo-fi slow BPM electro chill with organic samples". Prompt engineering may be applied to text-to-image models to achieve a desired subject, style, layout, lighting, and aesthetic. === Techniques === Common terms used to describe various specific prompt engineering techniques include chain-of-thought, tree-of-thought, and retrieval-augmented generation (RAG). A 2024 survey of the field identified over 50 distinct text-based prompting techniques, 40 multimodal variants, and a vocabulary of 33 terms used across prompting research, highlighting a present lack of standardised terminology for prompt engineering. Vibe coding is an AI-assisted software development method where a user prompts an LLM with a description of what they want and lets it generate or edit the code. In 2025, "vibe coding" was the Collins Dictionary word of the year. === Context engineering === Context engineering is a related process that focuses on the context elements that accompany user prompts, which include system instructions, retrieved knowledge, tool definitions, conversation summaries, and task metadata. Context engineering is performed to improve reliability, provenance and token efficiency in production LLM systems. The concept emphasises operational practices such as token budgeting, provenance tags, versioning of context artifacts, observability (logging which context was supplied), and context regression tests to ensure that changes to supplied context do not silently alter system behaviour. == Rationale == Research has found that the performance of large language models (LLMs) is highly sensitive to choices such as the ordering of examples, the quality of demonstration labels, and even small variations in phrasing. In some cases, reordering examples in a prompt produced accuracy shifts of more than 40 percent. === In-context learning === A model's ability to temporarily learn from prompts is known as in-context learning. In-context learning is an emergent ability of large language models. It is an emergent property of model scale, meaning that breaks in scaling laws occur, leading to its efficacy increasing at a different rate in larger models than in smaller models. Unlike training and fine-tuning, which produce lasting changes, in-context learning is temporary. Training models to perform in-context learning can be viewed as a form of meta-learning, or "learning to learn". === Prompting to estimate model sensitivity === Research consistently demonstrates that LLMs are highly sensitive to subtle variations in prompt formatting, structure, and linguistic properties. Some studies have shown up to 76 accuracy points across formatting changes in few-shot settings. Linguistic features significantly influence prompt effectiveness—such as morphology, syntax, and lexico-semantic changes—which meaningfully enhance task performance across a variety of tasks. Clausal syntax, for example, improves consistency and reduces uncertainty in knowledge retrieval. This sensitivity persists even with larger model sizes, additional few-shot examples, or instruction tuning. To address sensitivity of models and make them more robust, several evaluative methods have been proposed. FormatSpread facilitates systematic analysis by evaluating a range of plausible prompt formats, offering a more comprehensive performance interval. Similarly, PromptEval estimates performance distributions across diverse prompts, enabling robust metrics such as performance quantiles and accurate evaluations under constrained budgets. == Prompting techniques == === Multi-shot === A prompt may include a few examples for a model to learn from in context, an approach called few-shot learning. For example, the prompt may ask the model to complete "maison → house, chat → cat, chien →", with the expected response being dog. === Chain-of-thought === Chain-of-thought (CoT) prompting is a technique that allows large language models (LLMs) to solve a problem as a series of intermediate steps before giving a final answer. In 2022, Google Brain reported that chain-of-thought prompting improves reasoning ability by inducing the model to answer a multi-step problem with steps of reasoning that mimic a train of thought. Chain-of-thought techniques were developed to help LLMs handle multi-step reasoning tasks, such as arithmetic or commonsense reasoning questions. When applied to PaLM, a 540 billion parameter language model, according to Google, CoT prompting significantly aided the model, allowing it to perform comparably with task-specific fine-tuned models on several tasks, achieving state-of-the-art results at the time on the GSM8K mathematical reasoning benchmark. It is possible to fine-tune models on CoT reasoning datasets to enhance this capability further and stimulate better interpretability. As originally proposed by Google, each CoT prompt is accompanied by a set of input/output examples—called exemplars—to demonstrate the desired model output, making it a few-shot prompting technique. However, according to a later paper from researchers at Google and the University of Tokyo, simply appending the words "Let's think step-by-step" was also effective, which allowed for CoT to be employed as a zero-shot technique. ==== Self-consistency ==== Self-consistency performs several chain-of-thought rollouts, then selects the most commonly reached conclusion out of all the rollouts. === Tree-of-thought === Tree-of-thought prompting generalizes chain-of-thought by generating multiple lines of reasoning in parallel, with the ability to backtrack or explore other paths. It can use tree search algorithms like breadth-first, depth-first, or beam. === Text-to-image prompting === In 2022, text-to-image models like DALL-E 2, Stable Diffusion, and Midjourney were released to the public. These models take text prompts as input and use them to generate images. Early text-to-image models typically do not understand negation, grammar and sentence structure in the same way as large language models, and may thus requi

  Read more →
• 

  Learning augmented algorithm

  A learning augmented algorithm (also called algorithm with predictions) is an algorithm that can make use of a prediction to improve its performance. Whereas in regular algorithms just the problem instance is inputted, learning augmented algorithms accept an extra parameter. This extra parameter often is a prediction of some property of the solution. This prediction is then used by the algorithm to improve its running time or the quality of its output. The most common application are online algorithms, where a prediction on the uncertain instance is provided. == Description == A learning augmented algorithm typically takes an input ( I , A ) {\displaystyle ({\mathcal {I}},{\mathcal {A}})} . Here I {\displaystyle {\mathcal {I}}} is a problem instance and A {\displaystyle {\mathcal {A}}} is the prediction. A prediction can be any object. Common are the following types: Prediction of an optimal solution. The prediction gives a solution to the problem or characterizes an optimal solution. Prediction of the input. This is mainly used for online problems. Prediction of algorithmic actions. A prediction tailored to a specific algorithm that suggests a specific algorithm execution. Learning augmented algorithms usually satisfy the following three properties: Consistency. A learning augmented algorithm is said to be consistent if the algorithm can be proven to have a good performance when it is provided with an accurate prediction. Smoothness. A learning augmented algorithm is called smooth if its performance can be bounded by a function of the quality of the prediction. Here, the quality can be measured in a problem specific way. This is also called the prediction error. Robustness. A learning augmented algorithm is called robust if its worst-case performance can be bounded even if the given prediction is inaccurate. Learning augmented algorithms generally do not prescribe how the prediction should be done. For this purpose machine learning can be used. == Applications == A few examples of problems where learning augmented algorithms have been applied are the following. === Online algorithms === The ski rental problem The weighted paging problem The set cover problem Nonclairvoyant scheduling The online bipartite matching problem === Warm starting === ==== Data structures ==== The binary search algorithm is an algorithm for finding elements of a sorted list x 1 , … , x n {\displaystyle x_{1},\ldots ,x_{n}} . It needs O ( log ⁡ ( n ) ) {\displaystyle O(\log(n))} steps to find an element with some known value y {\displaystyle y} in a list of length n {\displaystyle n} . With a prediction i {\displaystyle i} for the position of y {\displaystyle y} , the following learning augmented algorithm can be used. First, look at position i {\displaystyle i} in the list. If x i = y {\displaystyle x_{i}=y} , the element has been found. If x i < y {\displaystyle x_{i} y {\displaystyle x_{i}>y} , do the same as in the previous case, but instead consider i − 1 , i − 2 , i − 4 , … {\displaystyle i-1,i-2,i-4,\ldots } . The error is defined to be η = | i − i ∗ | {\displaystyle \eta =|i-i^{}|} , where i ∗ {\displaystyle i^{}} is the real index of y {\displaystyle y} . In the learning augmented algorithm, probing the positions i + 1 , i + 2 , i + 4 , … {\displaystyle i+1,i+2,i+4,\ldots } takes log 2 ⁡ ( η ) {\displaystyle \log _{2}(\eta )} steps. Then a binary search is performed on a list of size at most 2 η {\displaystyle 2\eta } , which takes log 2 ⁡ ( η ) {\displaystyle \log _{2}(\eta )} steps. This makes the total running time of the algorithm 2 log 2 ⁡ ( η ) {\displaystyle 2\log _{2}(\eta )} . So, when the error is small, the algorithm is faster than a normal binary search. This shows that the algorithm is consistent. Even in the worst case, the error will be at most n {\displaystyle n} . Then the algorithm takes at most O ( log ⁡ ( n ) ) {\displaystyle O(\log(n))} steps, so the algorithm is robust. ==== More examples ==== The maximum weight matching problem === Approximation algorithms === The maximum cut problem The vertex cover problem === Mechanism Design === The facility location problem

  Read more →
• 

  Education by algorithm

  Education by algorithm refers to automated solutions that algorithmic agents or social bots offer to education, to assist with mundane educational tasks. These are often instrumentalist “educational reforms” or “curriculum transformations”, which have been implemented by policy makers and are supported by proprietary education technologies. New educational policies, mandated by transnational governance forums (like the OECD), have manufactured a connection between economies and education. Governments, schools and universities are expected to introduce or prepare students for an “unknown future”, to “future proof” them against an identified issue or to mitigate a national crisis. Technologies are seen as a catalyst to effect these changes. However, these policies mask a deeper problem, which include the assetization of education and the use of technologies as a means for surveillance and behavior modification. The traces that students and leave, through cookies, logins learning activities, assignments and tests, are collected, facetted, and shared with commercial organizations by these agents, to both predict future behavior and shape it. Techno solutionist thinking has led to managers adopting educational policies and reforms, and looking towards technologies to act as disrupters, liberators or agents to improve efficiency. During the COVID-19 pandemic, many more students had to modify their learning and working circumstances to protect themselves. Academics shifted their assessment practices from the dominant assessment of learning paradigm to an orientation that saw value in "assessment for learning". Big tech assisted, and teaching infrastructure became further privatized, and unbundling of education provision went a step further. Following the return to class, this assessment paradigm became rationalised in education. Leaving the space for algorithmic agents to step in. Academics work was increasingly driven by learning experience platforms and student understanding was extended through interleaving, behavior modification nudges and rewards and scheduled high stakes assessments. This data collection may also be construed as surveillance., or perceived as evidence of a Fourth Industrial Revolution

  Read more →