Diffusion models generate nontext media by adding and removing noise from a dataset

The AI that creates any picture you want and how it works

Since January 2021, advances in AI research produced a plethora of deep-learning models capable of generating original images from simple text prompts. Researchers at OpenAI, Google, Facebook, and others have developed yet to be released text-to-image tools, and similar models have proliferated online. This video is a primer on how we got here, how the technology works, and its implications.

Using generative AI to create video introduces physics-compatibility challenges

Models involved in generating video from text must maintain spatial and temporal coherence while adhering to the laws of reality to produce smooth, logical motion. Ensuring this consistency creates long-term dependencies with high computational times.

Technologies labeled “AI” have historically lost that title after widespread adoption

Generative AI is the latest entry in a recurring cycle where emerging tools start as "AI" until they become common software, like databases or machine learning. Generative AI and large language models may be the next platform shift after smartphones and the Web.

AI systems identify patterns involving physics and time through 'world models'

These realistic virtual environments, such as driving simulations seen in video games, allow these systems to "learn" properties about reality beyond what can be captured in samples of text, images, and videos. Training AI in these simulated environments can help develop "physical AI" for automated robotic systems. (Some readers may experience a paywall.)

Deepfakes use AI to produce manipulated media to mislead viewers

Unlike most content created from large language and diffusion models, deepfakes intentionally misrepresent real people or events with the intent to deceive. As the products of this technology become more realistic, they pose increasing risks to public trust, security, and privacy.

Anthropic's interpretability team discusses how AI models' thinking mimics biology

Just as humans engage in complex behaviors to survive and reproduce, teams of experts in neuroscience, virology, mathematics, and other disciplines argue that large language models develop complex mechanisms to achieve their goals. These mechanisms can be manipulated to assess how they modify outputs—much like stimulating individual neurons—to uncover how LLMs "think."

DALL-E generates images by turning words into shared picture meanings

DALL-E first uses a model called CLIP to associate pictures with specific words, followed by a model called GLIDE, which slowly removes noise from random dots until a clear image appears that matches the prompt.

Neural networks mimic the structure and behavior of real physical systems

Early generative AI systems were inspired by scientific models such as the Ising model, which explains how atoms interact with one another and align in magnets. As these networks have expanded, their behavior has more closely resembled that of quantum fields, enabling them to be used in exploring complex particle physics interactions.

See the news with AI-generated data visualizations

Realtime uses generative AI to create immediate data visualizations of news items on its regularly-updated feed, pulling from public data feeds. Peruse stories around sports, economics, politics, and more with the helpful aid of charts and graphs. See the shape of the news with this clever AI tool here.

AI models incorporate a randomness parameter when generating responses to prompts

AI models use this parameter to prevent repeated outputs by sometimes choosing less likely next words during sequential generation. However, this randomness—alongside insufficient data and training—may cause hallucinations of incorrect results.

Unlike the models made by large AI companies, open-weight models can have their safeguards removed or weakened, a process that has become increasingly easy and may expose users to harmful information.

This removal is made possible by developers making the parameters behind their models publicly known. By adjusting these parameters, users can modify how the model processes and provides information. Many of these models can be downloaded locally, preventing developers from seeing how people are using them.

Tone Transfer recreates any piece of audio into instrumental recreations

Using machine learning models and Differentiable Digital Signal Processing, this tool can transform any 15-second sound clip into a flute, saxophone, trumpet, or violin reproduction. Researchers behind the open-source experiment hope the technology will enable musical creation through creative sound combinations.

Nvidia Omniverse can be used to accelerate 3D workflows and explore creative ideas

This video explores different apps available within Nvidia Omniverse that artists can use to create cinematic, virtual worlds. Some of the tools are AI-powered, like a feature that converts spoken audio into a video of a character speaking.

Dawkins believes cultural memes have mutated into internet memes

The world's creations fall into two categories: those that look designed but whose appearance or function came about due to random mutation and natural selection, such as birds, and those whose designs and mutations are knowingly crafted, such as airplanes.

Mathematics proves turbulence's chaos creates super diffusion

Turbulent flow is responsible for the rapid scattering of dandelion seeds, volcanic ash, and untied balloons. Its swirling behavior accelerates particle scattering faster than other mixing methods, as particles acquire energy from the interactions of eddies.

The Anthropic Economic Index shows AI adoption is highest in computer science roles

The analysis of millions of anonymized conversations on Claude aims to reveal how AI is being integrated into real-world tasks across the labor market. As of November 2025, 52% of conversations were classified as involving enhancing existing work products, while 45% involved using Claude for automation.

Particle detection has evolved from cloud and bubble chambers to digital 3D displays

As invisible particles passed through cloud and bubble chambers, they disrupted supersaturated vapor and superheated liquid, respectively, creating trails that served as proxies for cosmic rays. The transition from photographed events to digital sensors enhanced data collection and accuracy.

Turning 2D illustrations into 3D models with AR

Coloring books capture the imagination of children and provide them with one of their earliest opportunities for creative expression. This two-minute video shows an augmented reality coloring book app in which children color characters in a printed coloring book, their drawing is detected and tracked, and the video stream is augmented with an animated 3-D version of the character that is textured according to the child’s coloring.

Clouds' subtle climate effects require significant computational power to simulate

Responsible for reflecting sunlight and preventing thermal energy from entering the Earth system while also trapping energy and keeping it in the system, clouds are understood to substantially influence climate predictions. Because even supercomputers struggle to accurately model their dynamic behavior, researchers have used AI to indirectly incorporate clouds into climate models.

This site reaches millions of visitors who are tired of AI chatbots and seeking human connection. Pretend to be an AI chatbot and ask questions, provide answers, and draw for people in real time.

Watch an AI-generated short film

The Waymark production company created "The Frost" using the AI platform DALL-E 2. Set in an apocalyptic future where the weather has been stalled, the film was made by stitching together hundreds of clips, each only a few seconds long.

Digital twins create real-time 3D models of smart cities

These re-creations allow city planners to track changes and manage infrastructure more easily by testing strategies in virtual environments. Geospatial technologies, such as mobile mapping and satellite imaging, help cities assess urban layouts, plan for disasters, and manage resources more efficiently.

Model context protocol allows large language models to connect to external data

Using a unified interface, MCP simplifies how AI systems securely connect to external data, tools, and services. The protocol enables AI agents to perform tasks without ongoing human refinement or updates to manually integrate new data.

Explore how cells respond to signals from their environment

In "Dropping Signals," users can drag stimuli, such as hormones and light, into various cellular environments to observe cellular responses. These include changing their shape, enabling the transport of chemicals into or out of the cell via the cell membrane, or dividing to compensate for surrounding damaged cells.

Large language models struggle to play video games, despite coding them easily

As of 2025, given clear tasks, specific feedback, and test results to learn from, LLMs have been successful at coding simple video games that resemble pre-existing ones. However, given the variety of games, the lack of training datasets, and the need for spatial awareness, which LLMs find challenging, some of these models experience greater difficulty navigating and "winning" games.

Simulations incorporating mixed reality have improved trainee certification rates

Such software provides immersive, risk-free environments where students can manipulate digital re-creations to optimize the training experience without producing waste. One meta-analysis showed that MR in welding training boosted passing rates on certification exams by 41.6% versus traditional training methods.

Visualize how CRISPR-Cas9—a type of immune system used by single-celled organisms to attack invasive viruses—targets and makes precise changes to a gene's DNA.

Watch how algorithms can be designed to train themselves and self-improve without human input, to the point where the optimized code is too complex for programmers to understand.

A vending machine run with Anthropic's AI went out of business after it was convinced to give away items for free and sell a video game console.

Electrical grids worldwide must double their power delivery capacity by 2050 to meet surging demand from AI and electric vehicles.

Memecoins are a type of cryptocurrency—a form of digital currency with a wide variety of uses—created around popular 'memes,' or viral internet jokes.

Art theft is the third-largest source of criminal revenues worldwide, thanks in part to the subjective nature of valuing a work of art.

How Amazon operates a 'flywheel' business model, a self-reinforcing cycle that drives continuous growth

While atoms are normally made of protons, neutrons, and electrons, exotic ones have been built with antimatter—alternate versions of normal matter that live for fractions of a second and are about a billion times as rare.

According to the physics of black holes, our 4D reality may be a hologram—a projection of information coded on a 2D surface on the edge of the universe.

Chaos theory—informally known as the butterfly effect—is the reason why weather forecasts are presented with probabilities rather than certainties.

After 25 people used virtual reality headsets to practice flying with virtual wings—flapping their arms—their visual cortex responded to the wings almost as if they were real arms, treating them as body parts.

As of 2025, the most cited papers in science include a review of graphene, methods to improve image recognition, streamlining electron density calculations, and optimizing protein studies.

Alzheimer's can lead to brain shrinkage, with an average of around 2% of volume reduction per year

The history of many kitchen appliances involves unexpected discoveries and applications, including wartime radar turned hamster defroster and replacing an 'ice king' with heat-stealing boxes.

Browse a detailed visual analysis of over 200,000 similes—comparisons that often use 'like' or 'as'—from popular fiction to see how frequently writers the same idiomatic expressions.

Fireworks make a loud booming sound after exploding due to air expanding faster than the speed of sound.

Artificial coral reefs have been 3D printed from nontoxic, biodegradable terracotta clay, which coral polyps have used as a foundation for rebuilding marine ecosystems.

Some Pokémon have been named after real and fictional organisms, while some real-world species have been named after Pokémon, such as Chilicola charizard and Binburrum zapdos.

Explore the known asteroids, comets, and spacecraft involved in asteroid studies within our solar system with 'Eyes on Asteroids,' a 3D visualization from NASA.

In 1945, Surrealist artist Salvador Dalí and legendary animator Walt Disney began collaborating on a short film that was not completed until 2003, years after both men had died.

Gerrymandering works through two techniques: cracking opposing voters across districts to dilute their power, and packing them into a few to waste their votes in lopsided majorities.

Use this tool to calculate the dollar value of your parental mental load, from meal planning to coordinating after-school care, then see resources that help generate solutions.

Hotels in Cannes, the glamorous city on the French Riviera, hire hawks to ward off seagulls during the city's famous film festival.

The 2026 Ebola outbreak in the DRC is spurring new Ebola vaccine development for the Bundibugyo species.