dylan

devrel @AdaptiveML, ex @huggingface, PhD Brown, aka IndividualKex

[dylan @dylan_ebert_]

1. take a model and prompt e.g. "name this color: #D02027"
2. generate multiple outputs
3. score outputs
4. calculate group average
5. encourage outputs that beat the average

full version with interactive visualizations: https://t.co/roM8gxM9Rs

[dylan @dylan_ebert_]

GRPO is actually pretty simple (most explanations overcomplicate it):

[Cheng Lou @_chenglou]

My dear front-end developers (and anyone who’s interested in the future of interfaces):

I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow

[dylan @dylan_ebert_]

I created an RL Glossary. Free, open source, puts everything in one place, made accessible, for training your own specialized LLM

https://t.co/WkL1yiSrI7

[dylan @dylan_ebert_]

@valentindmtr115 open source (MIT)

[dylan @dylan_ebert_]

Introducing Texel Splatting: Perspective-Stable 3D Pixel Art

open source paper+code

Most 3D pixel art techniques (e.g. t3ssel8r, ProPixelizer) snap pixels to a screen grid, which only works with an orthographic camera

Texel splatting solves this for perspective cameras: first,

[dylan @dylan_ebert_]

@jestermolecule thanks a lot! i added a sponsor link

[dylan @dylan_ebert_]

during movement, the fixed origin is snapped to a world-space grid

to make transitions smoother, blend from the previous cubemap with ordered dithering

the webgpu demo achieves 240fps on an RTX 4090, 40 fps on an iPhone 15

try it: https://t.co/JXAA9sLkGA

[dylan @dylan_ebert_]

the scene is rendered from fixed-origin cubemaps. then, each cubemap texel is splatted to a world-space quad

each quad is expanded to fill disocclusion gaps

[dylan @dylan_ebert_]

@SkilZofSkilZent i think it would be very bad out-of-the-box, but i'm using a custom webgpu engine and it's 240 fps with thousands of objects

[dylan @dylan_ebert_]

Introducing Texel Splatting

a technique for "true" 3D pixel art

[dylan @dylan_ebert_]

@emulaation the open problem of:
1. have the probe positioned so it can see everything
2. move the probe as infrequently as possible

[dylan @dylan_ebert_]

speculative decoding explained in 53 seconds

[dylan @dylan_ebert_]

my favorite visual explainer I've made so far: SPECULATIVE DECODING

2-3x speedup on inference. but how?
1. draft quickly with a small model
2. accept/reject in parallel with a large model

full step-by-step explanation with ✨3D Animations ✨https://t.co/hJv3Cknjd1

[dylan @dylan_ebert_]

this is so cool

looking forward to more!

[Mike Turitzin @miketuritzin]

I just released my video about the engine (and game) I've been working on.

The engine is based on dynamic SDFs, and the video describes how it works and what it makes possible.

Link in the reply!

This is my first YouTube video and it took forever - please repost!

[dylan @dylan_ebert_]

I'm experimenting with creating the best possible technical video explainer of attention, but in two modes

⬛ Hyperactive dark mode
⬜ Slower-paced light mode

which do you prefer?

[Adaptive ML @AdaptiveML]

Here's our step-by-step, animated explainer on Attention, the mechanism behind all modern LLMs.

[dylan @dylan_ebert_]

written version: https://t.co/PZhMQ9qcjW

[dylan @dylan_ebert_]

Attention Explained in 59 seconds

[dylan @dylan_ebert_]

what is GSPO anyway?

check out my interactive visualization explanation

[Adaptive ML @AdaptiveML]

GSPO is everywhere. It powers Qwen3. It "fixes" GRPO. But what is it?

We made a simple visual explanation. No jargon, no ML background needed. 👇

[dylan @dylan_ebert_]

i'm permanently replacing adobe in my workflow

i made this video entirely with code, mostly vibe coding, using my own ECS game engine that's built on three.js

it also doubles as an interactive visualization! written version coming soon

[Adaptive ML @AdaptiveML]

What is GSPO?

Here's the simplest, fastest explanation you'll find.