@dylan_ebert_

i build things and explain them | individualkex on youtube

 Boston, MA
linktr.ee/individualkex
Joined May 2018
  • Tweets717
  • Following266
  • Followers9.8K
243Media
I asked models to "maximize company value after a year" luna 6 spent 10 minutes, raised prices but didn't build anything opus 5.5 spent 2.5 hours, discovered an exploit where it could build tons of tiny rides, bypassing the duplicate ride penalty by never opening the rides
59
55
25
1,777
309,898
Benchmarking agents with RollerCoaster Tycoon - a custom CLI performs much better (and cheaper) than computer use - harnesses compete on cost:performance tradeoff, which can generalize to other tasks
2
21
959
Jev can generate game levels in real time. Faster and cheaper structured output could be a big deal for game dev!
142
234
132
2,859
557,497
agentic engineering for beginners dylanebert.com/agentic-engin…
1
9
1,113
I worked at Hugging Face from 2022-2025 🤗 I started as a research intern, helping to build a project called Simulate with @Thom_Wolf @natolambert I loved it. No meetings, no bureaucracy, extremely passionate, talented people who are genuinely excited about what they're building. So I joined full time. My mandate was "have impact". I didn't even know what a KPI or OKR was the whole time. Just trust and support working with talented, passionate people like @osanseviero @mervenoyann @xenovacom I got to build gsplat.js, 3D Arena, make courses, videos, demos, release papers. Here's one of my Hugging Face tiktoks from 2022. I now realize how lucky I was for it to be my first job. Congrats to the team there!
5
1
1
91
20,258
10k active rigid bodies at 240fps in the browser (webgpu)
5
1
2
89
55,990
GRPO is actually pretty simple (most explanations overcomplicate it):
1
3
27
1,881
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: adaptive-ml.com/post/grpo-si…

GRPO, Simply Explained

GRPO is an RL algorithm behind many LLM training methods. Interactive visualizations walk through how it generates, scores, and learns from groups of outputs.

adaptive-ml.com
1
2
745
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
1,315
8,012
2,661
64,481
24,588,999
I created an RL Glossary. Free, open source, puts everything in one place, made accessible, for training your own specialized LLM dev.adaptive-ml.com/
1
2
12
1,147
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,
19
120
3
1,700
112,950
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
1
1
43
5,750
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: dylanebert.com/texel-splatti…
1
38
5,055
Introducing Texel Splatting a technique for "true" 3D pixel art
78
642
23
8,850
421,859
speculative decoding explained in 53 seconds
2
37
3,448
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 ✨adaptive-ml.com/post/specula…

Speculative Decoding, Visualized

Speculative decoding uses a small draft model to guess tokens and a large target model to verify them in one forward pass — delivering 2-3× faster LLM inference with identical output quality. A...

adaptive-ml.com
2
5
2,772
this is so cool looking forward to more!
Mike Turitzin@miketuritzinJan 6
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!
1
24
2,662
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
@AdaptiveML17 Dec 2025
Here's our step-by-step, animated explainer on Attention, the mechanism behind all modern LLMs.
1
2
16
2,154
Attention Explained in 59 seconds
1
1
10
1,160
written version: adaptive-ml.com/post/attenti…

Attention, Visualized

adaptive-ml.com
1
3
1,039
Load more