https://ih.github.io/paying-attention-podcast/ en-us A 13-episode course that builds up the transformer, the engine inside modern artificial intelligence, starting from high school math, with every example drawn from robots and cameras. Two hosts, Maya and Leo, follow a robot arm named Sprocket as it learns to put the red block in the blue bowl. No visuals needed. Best heard in order. A 13-episode course that builds up the transformer, the engine inside modern artificial intelligence, starting from high school math, with every example drawn from robots and cameras. Two hosts, Maya and Leo, follow a robot arm named Sprocket as it learns to put the red block in the blue bowl. No visuals needed. Best heard in order. Paying Attention https://ih.github.io/paying-attention-podcast/cover.jpg https://ih.github.io/paying-attention-podcast/ false serial Yes The Big Picture 1 full How does a robot arm turn camera pictures and a typed sentence into motion? A bird's-eye tour of the transformer: chopping inputs into tokens, description cards made of numbers, a stack of blocks where tokens consult each other and think privately, and a readout that becomes a movement. Plus why transformers took over, and the catches. paying-attention-ep01 Sat, 10 Oct 2026 12:01:00 +0000 1566 false Seeing in Numbers 2 full How a camera turns a scene into numbers, why any list of numbers can be pictured as a point or an arrow, and the dot product, the simple multiply-and-add calculation that measures how well two lists match. We build a redness detector and an edge detector by hand. paying-attention-ep02 Sat, 10 Oct 2026 12:02:00 +0000 1478 false Chopping the World into Tokens 3 full How sentences become word pieces, pictures become tiles, and robot movements become clicks on a dial, and how every token gets a learned description card, called an embedding. Including how CLIP put pictures and captions into the same space. paying-attention-ep03 Sat, 10 Oct 2026 12:03:00 +0000 1422 false Building a Brain Cell 4 full The artificial neuron, built by hand as a grasp detector for Sprocket's fingers. Why one neuron can't detect "in the middle," why the bend matters, how layers and matrices work, why graphics chips are so good at this, and what vision networks learn layer by layer. paying-attention-ep04 Sat, 10 Oct 2026 12:04:00 +0000 1586 false Learning from Mistakes 5 full How machines learn from examples: recording demonstrations, measuring mistakes with a loss, walking downhill in the fog with gradient descent, and passing blame backward with backpropagation, all worked through with small numbers. Plus overfitting and snowballing errors. paying-attention-ep05 Sat, 10 Oct 2026 12:05:00 +0000 1497 false Why Attention? 6 full Why context matters so much, how convolutional and recurrent networks struggled with it, the 2014 and 2017 breakthroughs, and the core idea of attention: every token asks a question, wears a label, and offers a package of information. paying-attention-ep06 Sat, 10 Oct 2026 12:06:00 +0000 1529 false Attention, Step by Step 7 full The complete attention recipe, done with numbers small enough to do in your head: dot-product scores, dividing by a square root, the softmax, blending values, masks that stop peeking, and cross-attention. paying-attention-ep07 Sat, 10 Oct 2026 12:07:00 +0000 1541 false Many Heads and a Sense of Place 8 full Why transformers run many attention heads side by side, what researchers find those heads doing, why attention is blind to position, and four clever ways to tell the model where and when everything is. paying-attention-ep08 Sat, 10 Oct 2026 12:08:00 +0000 1471 false Inside the Block 9 full A complete transformer block: the feed-forward rulebook where much of the knowledge lives, mixture of experts, residual connections that add instead of replace, layer normalization as auto-exposure, and how a tile's card changes as it climbs the stack. paying-attention-ep09 Sat, 10 Oct 2026 12:09:00 +0000 1562 false From Thoughts to Actions 10 full How the final cards become movements: menus and softmax, action tokens versus direct numbers, the averaging trap that steers straight into the vase, temperature, noise-refining action heads, action chunks, and the tricks that make robot brains fast enough. paying-attention-ep10 Sat, 10 Oct 2026 12:10:00 +0000 1499 false Training a Robot Brain 11 full How robot brains are trained in practice: learning to see from internet pictures, the surprise score measured in bits, scaling laws, where robot data comes from, fine-tuning on demonstrations, small add-on dials, and learning from trial and error. paying-attention-ep11 Sat, 10 Oct 2026 12:11:00 +0000 1536 false The Family Tree 12 full Encoder-only, decoder-only, and encoder-decoder transformers, and the famous relatives in vision and robotics: the Vision Transformer, Swin, the Detection Transformer, Segment Anything, CLIP, RT-2, ACT, pi zero, the Decision Transformer, Gato, and world models. paying-attention-ep12 Sat, 10 Oct 2026 12:12:00 +0000 1553 false One Moment in the Life of a Robot Brain 13 full The finale: one decision followed through the whole machine with real numbers, from camera snapshot to motor commands, including recovering from a dropped block. Then the honest limits, safety, what's coming next, and the whole series in a nutshell. paying-attention-ep13 Sat, 10 Oct 2026 12:13:00 +0000 1559 false