Matt Henderson's banner

Matt Henderson

@matthen2 • 81,512 subscribers

maths, visualisations, conversational AI. VP Research @polyaivoice prev: @RekaAILabs, @Apple AI/ML, @GoogleAI, PhD @Cambridge_Eng

Shorts

returning to deepdream in the times of LLMs here I am using gemma 4 e4b, starting from a random image and optimizing its pixels to maximise the probability gemma captions them as a fantasy map with mountains, rivers, and castles actual AI art 😅

returning to deepdream in the times of LLMs here I am using gemma 4 e4b, starting from a random image and optimizing its pixels to maximise the probability gemma captions them as a fantasy map with mountains, rivers, and castles actual AI art 😅

34,643 просмотров

what if there was one chicken, with the same mass as all the world's chickens combined? it would be about 1.2km tall. what about one ant from all ant species? one cow? one human?

what if there was one chicken, with the same mass as all the world's chickens combined? it would be about 1.2km tall. what about one ant from all ant species? one cow? one human?

62,040 просмотров

what would a rainbow look like on an alien planet with binary suns? you get two rainbows at different angles - each with a different colour spectrum based on its star's temperature

what would a rainbow look like on an alien planet with binary suns? you get two rainbows at different angles - each with a different colour spectrum based on its star's temperature

56,475 просмотров

space filling curve

space filling curve

12,212 просмотров

uniform random noise + band-pass filter =

uniform random noise + band-pass filter =

34,869 просмотров

I have joined Reka, which today comes out of stealth to announce its Series A. It is an amazing group of people, with a convincing vision for the future of large generative models.

I have joined Reka, which today comes out of stealth to announce its Series A. It is an amazing group of people, with a convincing vision for the future of large generative models.

27,493 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

To solve a maze, keep the entrance cold and the exit hot. Once it settles, enter and always walk in the hottest direction.

To solve a maze, keep the entrance cold and the exit hot. Once it settles, enter and always walk in the hottest direction.

1,609,320 просмотров • 2 месяцев назад

Game of Life, using Minecraft recipes as the replacement rules

Game of Life, using Minecraft recipes as the replacement rules

235,944 просмотров • 2 месяцев назад

to tell if a maze is solvable, just hang it by its corners! The first maze stays in one piece, so there is no path from the entrance at the top to the exit at the bottom. The second maze splits apart along the solution.

to tell if a maze is solvable, just hang it by its corners! The first maze stays in one piece, so there is no path from the entrance at the top to the exit at the bottom. The second maze splits apart along the solution.

3,386,810 просмотров • 3 лет назад

What if our ears were like our eyes, and only had three receptors? Interestingly speech is still more or less intelligible, but not much else too me this shows how much more discriminating our hearing is than our vision

What if our ears were like our eyes, and only had three receptors? Interestingly speech is still more or less intelligible, but not much else too me this shows how much more discriminating our hearing is than our vision

192,678 просмотров • 2 месяцев назад

Game of Life on Penrose tiles

Game of Life on Penrose tiles

167,841 просмотров • 2 месяцев назад

what is a multimodal LLM thinking as it watches a video? Gemma 4 12B reads raw image patches, as if they were tokens. It was never trained to predict anything at these 'tokens' - but this video shows what it would predict if you did sample from its next token prediction head

what is a multimodal LLM thinking as it watches a video? Gemma 4 12B reads raw image patches, as if they were tokens. It was never trained to predict anything at these 'tokens' - but this video shows what it would predict if you did sample from its next token prediction head

164,051 просмотров • 3 месяцев назад

need to find the greatest common divisor of two numbers? just fold them on top of each other until you can't any more!

need to find the greatest common divisor of two numbers? just fold them on top of each other until you can't any more!

317,914 просмотров • 8 месяцев назад

how shaders work- using Excel =LET(x,(COLUMN()-24)/15,y,(ROW()-15)/15,SIN(SQRT(x*x+y*y)*10-t)) Each cell (pixel) computes its colour just from its coordinates- so the GPU can massively parallelise them. The trick is writing the formula to draw the picture you want

how shaders work- using Excel =LET(x,(COLUMN()-24)/15,y,(ROW()-15)/15,SIN(SQRT(xx+yy)*10-t)) Each cell (pixel) computes its colour just from its coordinates- so the GPU can massively parallelise them. The trick is writing the formula to draw the picture you want

113,343 просмотров • 2 месяцев назад

one easy way to make a simulation of falling sand piling up- just define what happens for all 16 possible 2x2 grids, and repeatedly apply these rules to the picture

one easy way to make a simulation of falling sand piling up- just define what happens for all 16 possible 2x2 grids, and repeatedly apply these rules to the picture

1,048,528 просмотров • 3 лет назад

Deep dreams on modern LLMs are so cool (optimizing an image to maximize P(target caption)) Gemma 12B (left) has no vision encoder — it reads pixels like token embeddings — and stamps recognisable objects around the canvas. E4B (right) has one, and drifts to texture instead.

Deep dreams on modern LLMs are so cool (optimizing an image to maximize P(target caption)) Gemma 12B (left) has no vision encoder — it reads pixels like token embeddings — and stamps recognisable objects around the canvas. E4B (right) has one, and drifts to texture instead.

95,378 просмотров • 3 месяцев назад

does your audio-input LLM secretly know how to generate speech? yes but it sounds like a scary demon! deepdream but for speech: starting with noise audio, I tried optimizing the probability of a desired transcription, while keeping the model frozen. volume up! 🎧

does your audio-input LLM secretly know how to generate speech? yes but it sounds like a scary demon! deepdream but for speech: starting with noise audio, I tried optimizing the probability of a desired transcription, while keeping the model frozen. volume up! 🎧

86,766 просмотров • 3 месяцев назад

a version 1 QR code with maximum error correction can store 7 bytes. That’s 2⁵⁶ possible codes. Here are the first 1,043 of them-

a version 1 QR code with maximum error correction can store 7 bytes. That’s 2⁵⁶ possible codes. Here are the first 1,043 of them-

175,433 просмотров • 8 месяцев назад

an exponential curve looks identical anywhere along the x axis- so long as you stretch the y axis accordingly

an exponential curve looks identical anywhere along the x axis- so long as you stretch the y axis accordingly

570,344 просмотров • 3 лет назад

searching for Life

searching for Life

42,194 просмотров • 2 месяцев назад

can you see the spinning dodecahedron? pause the video and it disappears

can you see the spinning dodecahedron? pause the video and it disappears

303,686 просмотров • 2 лет назад

can a neural network learn to walk as a physical object in a physics simulation? here I train walking neural nets with an evolutionary algorithm. The input nodes/feet are activated by sine waves at learned phases & connections between two neurons extend based on their difference

can a neural network learn to walk as a physical object in a physics simulation? here I train walking neural nets with an evolutionary algorithm. The input nodes/feet are activated by sine waves at learned phases & connections between two neurons extend based on their difference

339,447 просмотров • 3 лет назад

hello world in python... using a genetic algorithm

hello world in python... using a genetic algorithm

196,034 просмотров • 2 лет назад

Minesweeper, but on the new Einstein tiles

Minesweeper, but on the new Einstein tiles

241,244 просмотров • 3 лет назад

a fun way to draw a picture from the digits of pi, made from circular arcs. draw an arc that goes 3/10 of the way around the circle. Now flip the circle over and continue the curve by drawing another arc 1/10 around, 4/10, 1, 5, 9 etc. following the digits of pi

a fun way to draw a picture from the digits of pi, made from circular arcs. draw an arc that goes 3/10 of the way around the circle. Now flip the circle over and continue the curve by drawing another arc 1/10 around, 4/10, 1, 5, 9 etc. following the digits of pi

186,931 просмотров • 3 лет назад

prime factorization trees

prime factorization trees

186,836 просмотров • 3 лет назад