language

Rob Miles explains on Computerphile how language models generate plausible text and how transformers improved on recurrent networks, with a look at what comes next.

Rob Miles discusses GPT-3 on Computerphile, covering how scaling parameters kept improving results over GPT-2 and how the model nearly learned arithmetic without anyone knowing exactly how.

3Blue1Brown's visual explanation of how transformers and GPT-style language models work, tracing data through tokens, embeddings and attention.

Vsauce's explainer on Zipf's law, the pattern in which the frequency of a word is inversely related to its rank. It shows the pattern across many domains and discusses why it remains unexplained.

Linguist Geoff Lindsey explores vocal fry: what it is, who uses it, how it relates to glottal stops and accents, and why some people dislike it.

Dialect coach Erik Singer and several linguists tour distinct accents across English-speaking North America. It is the first part of a WIRED series on US accents.

Benn Jordan explains how Flock Safety's license plate cameras log and share vehicle locations, and explores how adversarial AI can defeat them. It covers weak security and the surveillance risks of private police-camera networks.

3Blue1Brown's visual walkthrough of the attention mechanism inside transformers, covering self-attention, multiple heads and cross-attention. It is chapter 6 of his deep learning series.

Yannic Kilcher walks through the Attention Is All You Need paper, which introduced the Transformer, a sequence model based solely on attention without recurrence or convolutions. He reviews the architecture and the paper's translation results.

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 Welch Labs explainer on neural scaling laws and the compute-efficient frontier, asking why model loss seems to hit a line it cannot cross. It draws an analogy to an ideal gas law for AI.

Musician Benn Jordan explains and demonstrates adversarial noise that poison-pills music files against AI training and scraping.

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.

An animated introduction to geometric algebra, presented as a language that can describe most of physics. It was made with manim and covers multivectors and how they generalize familiar tools like cross products and quaternions.

A Veritasium video on how a feud between Russian mathematicians led to Markov chains and the modern prediction algorithms built on them. It covers the history and the math behind them.

Geekerwan's Chinese-language review of Intel's Lunar Lake lightweight laptop chip, covering performance, perf-per-watt curves and battery life benchmarks. It tests whether x86 can compete on efficiency.