image classification

A guest video by Welch Labs on 3Blue1Brown explaining how text-to-image and video models work. It covers CLIP, shared embedding spaces, diffusion models (DDPM, DDIM), conditioning, guidance and negative prompts.

Lesson 1 of fast.ai's Practical Deep Learning for Coders, taught by Jeremy Howard. It takes coders from running code in a Jupyter notebook straight into training a real image model.

Alex O'Connor shows that ChatGPT cannot draw a wine glass filled to the brim, and ties the failure to David Hume's missing shade of blue. It asks what the failure says about how image models learn.

A short side-by-side demo of a large image loading over a slow connection in JPEG, progressive mozjpeg, JPEG XL and AVIF. It shows how each codec renders partial data.

Benn Jordan's video about storing a PNG image in a living bird, a starling that learns to reproduce encoded sounds. It mixes ornithology, audio engineering, and data encoding.

Veritasium visits the US Navy's Crane facility to test top night vision goggles. It explains how image intensifier tubes and thermal or digital systems work and compares the generations of the technology.

A short demo of an open-source Krita plugin that uses Stable Diffusion to generate and edit images in place. It adds ControlNet scribble and line-art support. You select an area, push a button, and new matching content appears.

A 2023 University of Toronto conversation between Geoffrey Hinton and Fei-Fei Li on responsible AI development. They look back at the history of deep learning and ImageNet and discuss the ethics and risks of AI.

3Blue1Brown introduces group theory and abstract groups, then builds toward classification of finite simple groups and the enormous Monster group with its 196,883 dimensions.

A short Techquickie explainer on why laptop webcams are much worse than phone cameras. It covers sensor size, image processing, and the interface differences between laptops and phones, with input from a Logitech engineer.

GeoGuessr pro Rainbolt plays head-to-head against an AI built by Stanford students that guesses locations from street-view images. The video shows the AI repeatedly beating him.

Robert Erdmann, a materials scientist at the Rijksmuseum, gives a PyCon keynote on the ultra-high-resolution imaging of Rembrandt's Night Watch. He covers the automated gantry camera system, the Python software that drives it, and the large volumes of image data involved.

Inigo Quilez live-codes a cartoon character painting entirely from math, using signed distance fields in a Shadertoy shader. He explains each step of building the image from formulas.

Explains the proposed NASA JPL plan to use the Sun as a gravitational lens, sending solar sail craft to its focal region to image an exoplanet's surface. It covers the distances involved, how imaging with the Sun would work and the mission design.

PBS Space Time explains the proposal to use the Sun's gravity as a giant lens, sending a train of small light-sail spacecraft to the focal point roughly 550 AU out. It covers how such a telescope could image exoplanets in surprising detail and the engineering challenges involved.

Myst co-creator Rand Miller recounts how the HyperCard-built game struggled to run on 1x CD-ROM drives. He and his brother Robyn compressed image and audio data heavily to get acceptable performance. Part of Ars Technica's War Stories series.

Wes Bos breaks down the techniques behind the McMaster-Carr website's speed: server-rendered HTML, prefetching, CDN and service worker caching, preloading, critical CSS and fixed-size images. He also notes its old-school jQuery and YUI JavaScript.

Physicist Angela Collier's nearly three-hour critique of Richard Feynman's public legacy. She examines how his books, written with Ralph Leighton, shaped a mythologized great-man image, and covers his personal behavior.

DIY Perks builds a webcam mod using a two-way mirror in a box so the camera sits behind the screen image. This allows real eye contact on video calls.

Tom Scott visits the USPS Remote Encoding Center in Salt Lake City, where keyers decipher mail images machines cannot read. It shows the lengths taken to decode bad handwriting.

Fraser Cain interviews JPL physicist Slava Turyshev about using the Sun's gravity as a lens to image distant exoplanets. They cover how the lens works, how a spacecraft would align with it, and mission design.

A video presenting an Intel research paper on enhancing the photorealism of synthetic images. A convolutional network uses rendering intermediates, shown on GTA V footage that comes out looking like real street scenes.

Jacob Geller's video essay on empty cities and what they say about our relationship to places, using games, literature and aerial imagery. It touches on works such as Invisible Cities.

Retro Game Mechanics Explained shows how the Atari 2600 draws images with almost no video memory, by having the CPU race the CRT beam line by line. It walks through the techniques in detail.

Physicist and YouTuber Angela Collier argues in this hour-long video that AI as commonly described does not really exist. She covers the limits of the tools, biased datasets, and why they should not be used to make decisions.

A short demo of interactive AI live painting in Krita using the Stable Diffusion plugin, where canvas changes update the generated image immediately. It uses an LCM sampler for speed and needs a high-end GPU for the interactive feel.

A Some More News episode critical of Elon Musk, covering his public image, billionaire behavior, the Boring Company and the push to Mars.

A step-by-step tutorial on making a Harry Potter by Balenciaga style AI video, using tools such as ChatGPT, Midjourney and Eleven Labs for script, images and voices.

A German STRG_F investigation into why child sexual abuse material stays online on forums, following a father whose daughter's abuse images were widely shared. The reporters tried to get the content removed by contacting hosters.