Visualize how transformer architecture generates an LLM's outputs

LLMs explained simply and quickly

Large language models generate responses by predicting one token at a time, based on patterns they’ve learned from massive datasets. This explainer covers their core components: data, architecture, training, and how transformer models use context to simulate conversation.

Transformer architecture can recognize and predict patterns in language

The underlying software powering text generation in AI tools associates each word or subword—called a token—with a set of values corresponding to how often it appears near other tokens. By recognizing these associations in prompts, the LLM can infer meaning.

View a timeline of AI deployments from 2017 to 2025

The development of transformer architecture and the release of GPTs across AI labs led to rapid changes in LLM scale and power. Companies like OpenAI, Google, Meta, Microsoft, and Anthropic have invested billions of dollars to develop reliable, versatile models.

LLMs are the backbone of AI tools that process and generate natural language

Large language models identify patterns in massive datasets of books, code, and unlabeled text from which to generate coherent responses. GPT-3 was trained on about 45 terabytes of data and uses 175 billion parameters—each parameter being a value the model adjusts as it learns.

How ChatGPT learns to read

The introduction of ChatGPT last fall jumpstarted public interest in the future capabilities of artificial intelligence and what it means for society. Of many somewhat "jargony" terms thrown around, the phrase "Large Language Model" is commonly seen—but also incredibly unclear as to what it means. In the simplest sense, the programs comb through mountains of internet data in response to a question and guess at what should come next (subscription needed).

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."

Neural networks are modeled after an idealization of the brain

These networks—including the backbone of ChatGPT-3, which has approximately 175 billion parameters—naturally discover the implicit rules of grammar and syntax within language by identifying patterns. Deviations in word patterns add creativity to the text generation.

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.

Temperature is a value that controls how predictable or creative an LLM's output is

In large language models, temperature adjusts the randomness in text generation by modifying how often words with lower probabilities are selected next in the sequence. Lower temperatures produce more obvious outputs while higher temperatures produce more creative responses.

Trick an LLM into revealing sensitive information

Even with robust training, large language models may be fooled into providing sensitive information if correctly prompted. In this game, a wizard withholds eight passwords, which you must prompt them to reveal with ever-increasing LLM safeguards.

Art and video produced through generative AI involve competing neural networks

Generative adversarial networks are a type of deep learning architecture that consists of a generator, which creates data that appear real, and a discriminator, which attempts to distinguish authentic from fake data. The two train in a competitive loop until the real and fictional data are indistinguishable.

Explore an interactive graphic of a wind turbine's components

Wind turbines contain a gearbox that increases the rotation of the blades by a factor of 100 from low to high-speed shafts. The latter moves magnets that change the magnetic field within a generator, creating electricity.

How electrical transformers use coils of conductive wire to change voltage levels

Two sets of wires are wrapped around a magnetic core, each a different number of times. As alternating current flows through one wire, it generates a changing magnetic field that induces an alternating current in the second wire. If the second wire has fewer coils, the voltage steps down—decreases. If the second wire has more coils, the voltage steps up.

View a breakdown of the mathematics behind the Standard Model

The Lagrangian version of the theory—related to the system's energy—presents a vast mathematical equation, with different components representing various force interactions and types of particles, including ghost particles to cancel out mathematical redundancies.

What are neural networks and why do they matter?

Learn how a neural network works, why it matters, and how it can be trained to recognize patterns, classify data, and forecast future events.

Generate a powerpoint filled with 'consulting slop' for your business

Created by the consulting company NOBL, this AI generator mimics and mocks the vague and impersonal presentations sometimes shared by consulting firms.

A lot of high fantasy relies on constructed languages

In "Lord of the Rings," there's Elvish. In "Avatar," it's Na'vi. In "Game of Thrones," it's Dothraki. The languages draw readers into these fictional stories, imbuing the worlds with a sense of realism. Linguist John McWhorter argues these are real languages because they have grammatical rules and evolve over time.

Visualizing the built world compared to the natural world

In the last century, humans have covered the Earth in 1,300 metric gigatons of built material, known as technomass. That amount is more than the Earth's entire biomass at 1,100 GT, which includes all living organisms. To get a sense of the scale of this comparison, click through this striking, simple visualization showcasing the various organisms comprising biomass as well as the materials making up the technomass.

Learn more about Palantir's core products, Gotham and Foundry

Palantir's core products, Gotham and Foundry, are designed to help government agencies and businesses turn complex or messy datasets into usable information. Gotham is designed primarily for government clients and connects disparate data points into recommendations and analysis. Foundry is designed for enterprise users.

Visualization of printing synthetic DNA

Ever wonder how synthetic DNA is made? Discover how GenScript uses innovative technology to synthesize precise, high-quality DNA at a larger scale than ever before.

See top-down views of Washington state's geology with cutting-edge lidar

Lidar is a revolutionary tool that creates visual models of landscapes using rapid light pulse measurements. Geologists in Washington state have deployed the technology to study the state's fault lines, landslides, tsunami inundation zones, and much more.

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.

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.

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.

What is the brain up to when the mind wanders?

As you stare into the distance while washing your home's seemingly never-ending pile of dishes, the brain activates its default mode network. This collection of "task-negative" brain regions associated with memory, reward, action consideration, and prediction alight with activity when humans mentally turn inward, possibly giving rise to the brain's ability to wander and humans' ability to construct internal narratives about the world.

Explore the components of the linear particle accelerator at Los Alamos

Located at the site of bomb design and development for the Manhattan Project, LANSCE features an injector system for hydrogen ions, a series of tanks with alternating electric fields for proton acceleration, and an isotope production facility that creates radioisotopes for medical treatments.

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.

Explore our favorite visualization of the immense scale of space, from an astronaut to the size of the observable universe

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

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

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.

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

Dirty lightning is a thunderstorm created from friction between rising and falling flows of ash and smoke during volcanic eruptions.

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.

In 2025, four executives from large tech companies were given positions in the US Army Reserves—including Palantir Chief Technology Officer Shyam Sankar, which reinforced Palantir's ties with the US military and its role as a leading defense partner.

Recent research found that the brain doesn't seem to massively rewire following amputation—upending earlier beliefs about the cause of phantom limb pain.

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.

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

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.

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.

The power and influence of the American presidency have expanded significantly over time—far beyond what the founders envisioned.

The animatronic shark from Steven Spielberg's 'Jaws,' the first modern blockbuster, was a complex underwater apparatus called 'Bruce.'

See a 3D reconstruction of Tenochtitlan, the Aztec capital that was home to an estimated population of 200,000 to 400,000.

The Mona Lisa's celebrity status and repeated restorations have obscured what made the painting so revolutionary for its time

In 2019, a laptop loaded with six of the worst malware in history and described as 'an exhibit of historical weaponry' sold for $1.3M.

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.

Watch what the Ebola virus does inside our cells and organs in order to spread and survive.

The Brothers Grimm were lawyers before they were storytellers, and became interested in fairy tales as they began investigating how rules and customs had been passed down through cultures.

Famed poet TS Eliot rejected the manuscript for George Orwell's political fable 'Animal Farm,' writing that its criticism of authoritarianism was not 'the right point of view.'

Watch how deep-sea mining equipment collects and processes polymetallic nodules—metal-rich, potato-shaped rocks—from the ocean floor and creates environmentally damaging plumes of sediments.