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

Explore a gallery of DALL-E creations

OpenAI's text-to-image generator can create content in a wide range of image styles based on simple prompts. Its utility has also given rise to an organic, passionate user base who employ the tool both for fun and for professional purposes.

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

Unlike text-based AI tools, which rely on large language models to recognize patterns in text, diffusion models use a reward system to generate images, video, audio, and 3D models. They can also be customized to match a user’s style.

Play 'Quick, Draw!' to help train Google's neural networks

Players are tasked with drawing objects, and Google’s AI—which has been trained on millions of user-submitted doodles—tries to guess what’s being sketched. Over 50 million drawings across 345 categories have been created and can be reviewed by users.

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.

When you complete a CAPTCHA on a website to prove you are human, you may be unknowingly training algorithms for self-driving cars, whose systems require training data to help identify crosswalks, bicycles, and other outdoor objects.

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.

AI vs. machine learning vs. deep learning

Machine learning is best understood with visuals. A collection of the best 9 images, videos and flowcharts that explain what it is and how it works.

Help scientists at LIGO train AI to resolve glitches in observational data

Volunteers are provided with visual representations of signal abnormalities at various frequencies and tasked with categorizing them based on reference examples. Progressing through the tool unlocks more difficult images and additional features. Categorized images will be used to train machine learning algorithms for automated future classification.

LLMs are trained via modeling, imitation learning, and reinforcement learning

Training large language models begins with pretraining the model to predict the next word in a sequence based on finding patterns in massive amounts of text. Patterns are then fine-tuned to model human-written dialogue and to align responses with user preferences.

Teaching a robot to laugh

Researchers have designed a shared-laughter AI system that responds to human laughter in order to build a sense of empathy into dialogue. Learn how they did it with this explainer.

The hardware powering AI was originally designed for video game graphics processing

Graphics processing units are specialized computer chips that can process multiple data streams in parallel, including pixel colors for a display. Such processing is required to find connections across text data and generate outputs quickly.

Office Assistants, including Clippy, were digitally edited with Macintosh computers

The animated characters served as intelligent user interfaces for Microsoft Office and were sketched by hand before being scanned. Clippy was selected as the default assistant after social psychologists at Stanford University identified it as the most trustworthy, likable, and humorous character based on public testing.

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.

When you complete a CAPTCHA on a website to prove you are human, you may be unknowingly training algorithms for self-driving cars, whose systems require training data to help identify crosswalks, bicycles, and other outdoor objects.

Roy Lichtenstein popularized benday dots in his famous comic-inspired paintings

American newspaper publisher Benjamin Henry Day Jr. developed the "benday" printing and photoengraving technique to produce grays and colors with fine patterns of ink of equal size and distribution. The process would become widespread in newspaper printing and define the work of Roy Lichtenstein.

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.

Explore persistent 3D environments with Marble

Marble is a spatial AI system built by World Labs, a San Francisco startup focusing on world models (rather than large language models). Using a text prompt (or a single image or video), users can generate a "world" and move through it, edit it, or export it. The company and project are part of the broader spatial intelligence area of AI, where AI can simulate environments.

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.

Button boards may be the next step in human-canine communication

In a viral trend, dogs have been recorded using button boards to seemingly "talk" with humans. Researchers are divided on whether this means dogs have learned language or are engaging in sophisticated behavioral conditioning.

Why does that bag look like a face?

If you've ever spotted a face hidden in an inanimate object, you've engaged in a timeless phenomenon known as pareidolia. This three-minute video explains why and how it happens.

Watch how the Enigma machine encrypts messages and learn about its critical design flaw

Using settings selected from a series of rotors and a plugboard that let operators swap letters with any of their choosing, the machine lit up the output letter for each letter typed. While this system could generate messages requiring any of 150 quintillion potential keys, the machine's reflector never encrypted a letter as itself, providing an entry point for exploiting the system.

Breaking down Anthropic's products and why their models are named after literary forms

Since March 2024, the Claude series of large language models includes three varieties—Haiku, Sonnet, and Opus—named to metaphorically illustrate increasing complexity and computing power. Claude Code can perform software engineering tasks for developers and, as of January 2026, writes nearly all of Anthropic's code alongside Opus 4.5.

How Scrabble got its name

Alfred Butts, a newly unemployed architect during the Great Depression, created Scrabble. But the game was named by James Brunot, who used the word to describe the most common action its players take part in: digging frantically.

FLOW-MATIC was the first programming language resembling the English language

As part of the team working on UNIVAC—the first commercially produced electronic digital computer in the US—Grace Hopper helped develop the system that enabled nonprogrammers and businesspeople without a strong mathematics background to use the machine effectively, thereby enhancing the computer's commercial viability.

How Emily Dickinson poetically deployed the em dash

Dickinson had many purposes for dashes in her poems: Sometimes they serve rhythm, sometimes they reflect the naturally fragmented way we tend to speak, and sometimes they are a simple artistic choice. This quick explainer breaks down how dashes work grammatically and how they operate in some of Dickinson's verses.

Dalí partnered with Hallmark to design surreal Christmas cards

Dalí pursued commercial work throughout his career. In 1948, Hallmark released a set of Christmas cards designed by the artist. A decade later, he created images for additional holidays, including Valentine's Day, Easter, and Mother's Day.

How people imagine a calendar year

It turns out everybody imagines the abstract calendar year in a simple, concrete way, though there are surprising differences between the exact model and shape of each image. Dive into one writer's collection of tens of thousands of questionnaire responses showing the fascinating consistency and divergence of how people visualize time.

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.

Massive blooms of microscopic plankton called dinoflagellates produce the neon blue light seen in glowing tides.

English mathematician Ada Lovelace wrote the first computer algorithm a century before computers existed and hypothesized that computing devices would one day be able to compose music—foreseeing the generative AI systems of today.

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.

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.

Elk Cloner, the first computer virus to spread in public, was written as a practical joke by Richard Skrenta, a Pittsburgh high school student.

Watch this video that uses Lego bricks to explain how venture capital works.

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

Mid-century modern graphic designers, known for their bright colors and bold lines in advertising, also found success with children's books.

Search a massive database of over 4 decades of clues from the TV quiz show 'Jeopardy!'

Objects can be 3D printed with light by projecting 2D computerized tomography (CT) scans onto rotating cylinders of resin, which solidify upon exposure.

The first image of a black hole was captured by creating an Earth-sized virtual observatory from a network of eight radio telescopes.

Power lines are dotted with large, brightly colored balls to improve the visibility of these thin wires to helicopters and small planes and help prevent potential crashes.

A pickleball's loud 'pop' sound can reach 120 decibels, which is equivalent to a hammer hitting a nail

Fear or disgust related to clusters of holes and cracks, called trypophobia, may stem from evolutionary processes to help us avoid pathogens.

Explore chaos in this simulation of two double pendulums, where small differences in the release angles produce wildly different outcomes.

The word 'jazz' evolved from 'jasm,' 19th-century American slang for 'energy'

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.

The story of Dollree Mapp, whose legal challenge over her 1957 conviction for possessing "obscene material" led to a major strengthening of the Fourth Amendment

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.

Fast-casual restaurant Chili's is experiencing a resurgence, with its parent company recently reporting a nearly 32% increase in sales, thanks to passionate Gen Z fans on TikTok.

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.

'Grand Canyon of the Yellowstone,' a work by American painter Thomas Moran, inspired Congress to establish Yellowstone National Park.