Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Finally found a meaningful scenario for running LLM in the browser, peering into the internals of LLM to see what's really happening inside

Brooooook_lyn's profile picture

Broooooklyn

7,395 subscribers

46,567 Aufrufe • vor 4 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Broooooklyn
Broooooklynvor 4 Monaten

You can even inspect the prompt!

Profilbild von Broooooklyn
Broooooklynvor 4 Monaten

This is a real @Alibaba_Qwen 3.5 0.8b mlx running, not some mock animation

Profilbild von Broooooklyn
Broooooklynvor 4 Monaten

replace the llm course on @huggingface with this

Profilbild von Gregor
Gregorvor 4 Monaten

wait the LLM is literally watching itself

Profilbild von Matt Rickard
Matt Rickardvor 4 Monaten

cool

Profilbild von 花椰菜
花椰菜vor 4 Monaten

這個太酷了 能不能把它整合進像是 omlx UI 裡面 每次運作如果都這樣顯示 那就太炫技了

Profilbild von Kongmoumou
Kongmoumouvor 4 Monaten

would u open source it 🤩

Profilbild von Broooooklyn
Broooooklynvor 4 Monaten

It's open sourced But I don't have time to write documentation on how to build and run it.

Profilbild von Dao WuMing
Dao WuMingvor 4 Monaten

mark, this cool, i maybe make video intro😃

Profilbild von Lyubomir
Lyubomirvor 4 Monaten

This is super cool 🫡

Profilbild von Chirag
Chiragvor 4 Monaten

@grok whats happening here?

Ähnliche Videos

INTRODUCING Notte Building the agentic internet with the strongest web browser for LLM agents. We transform ANY webpage into structured text, enabling better web understanding and navigation. Plug any LLM to to build your own AI agent
0:39

INTRODUCING Notte Building the agentic internet with the strongest web browser for LLM agents. We transform ANY webpage into structured text, enabling better web understanding and navigation. Plug any LLM to to build your own AI agent

Notte

225,226 Aufrufe • vor 1 Jahr

Incredible things happening in the LLM psychosis community
0:40

Incredible things happening in the LLM psychosis community

Justine Moore

573,629 Aufrufe • vor 9 Monaten

JSX Tool (@jsxtool) is an in-browser IDE for building React UIs. Click on any element in the browser to jump straight to the relevant line of code and edit it yourself or provide precise context to an LLM to make updates.
3:51

JSX Tool (@jsxtool) is an in-browser IDE for building React UIs. Click on any element in the browser to jump straight to the relevant line of code and edit it yourself or provide precise context to an LLM to make updates.

Y Combinator

49,755 Aufrufe • vor 11 Monaten

The harness can make a difference in AI for CAD. Below: same LLM (Opus 4.8) with different harnesses. Looking forward to see more progress without waiting for a new LLM version :) (Good job Paul Fremantle)
0:30

The harness can make a difference in AI for CAD. Below: same LLM (Opus 4.8) with different harnesses. Looking forward to see more progress without waiting for a new LLM version :) (Good job Paul Fremantle)

Michael Rabinovich

42,093 Aufrufe • vor 3 Monaten

Free Mode is live in Higgsfield Supercomputer. The LLM inside is now free to use for brainstorming, prompt writing, scripting, research, and project planning. Credits kick in only when you generate. A Supercomputer-level LLM, yours to use.
0:43

Free Mode is live in Higgsfield Supercomputer. The LLM inside is now free to use for brainstorming, prompt writing, scripting, research, and project planning. Credits kick in only when you generate. A Supercomputer-level LLM, yours to use.

Higgsfield AI 🧩

267,347 Aufrufe • vor 2 Monaten

if you wanna start building LEGO in the browser, you can get pretty far telling your llm to use ldraw + three.js
0:45

if you wanna start building LEGO in the browser, you can get pretty far telling your llm to use ldraw + three.js

jhey ʕ•ᴥ•ʔ

66,799 Aufrufe • vor 1 Monat

stress_test.mp4 c++ rewrite finished. 1.5 months. ~6 billion LLM tokens spent through codex runs at 60 fps in the browser (~120-180 uncapped). every tree and sprite and texture is LLM authored.
0:20

stress_test.mp4 c++ rewrite finished. 1.5 months. ~6 billion LLM tokens spent through codex runs at 60 fps in the browser (~120-180 uncapped). every tree and sprite and texture is LLM authored.

scaredofboobs🪲

53,733 Aufrufe • vor 3 Monaten

My friend applied to 250 tech jobs in two years. No MIT. No Stanford. No PhD. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. Andrej Karpathy's 4-hour course on "How to build a full LLM from scratch." Anthropic's own researcher gives up the exact playbook behind building LLMs like ChatGPT & Claude. I watched it last night. Halfway through, I realized I could break into an AI lab in months, not years. Bookmark this and read the article below. • 00:00 - LLMs as new OS • 40:58 - LLM tokenization architecture • 53:22 - LLM neural network internals • 1:04:20 - LLM pretraining • 3:21:37 - LLM RLHF & DeepSeek R1
3:54:58

My friend applied to 250 tech jobs in two years. No MIT. No Stanford. No PhD. Last month Anthropic offered him $750,000. I asked him how he broke in from zero. He sent me the exact video that got him in. Andrej Karpathy's 4-hour course on "How to build a full LLM from scratch." Anthropic's own researcher gives up the exact playbook behind building LLMs like ChatGPT & Claude. I watched it last night. Halfway through, I realized I could break into an AI lab in months, not years. Bookmark this and read the article below. • 00:00 - LLMs as new OS • 40:58 - LLM tokenization architecture • 53:22 - LLM neural network internals • 1:04:20 - LLM pretraining • 3:21:37 - LLM RLHF & DeepSeek R1

Roan

124,745 Aufrufe • vor 2 Monaten

Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)
0:23

Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)

Brendan Bycroft

1,203,096 Aufrufe • vor 2 Jahren

Today we're launching 2.0, the in-browser Postgres sandbox with AI assistance - now with bring-your-own-LLM 🚀
2:41

Today we're launching 2.0, the in-browser Postgres sandbox with AI assistance - now with bring-your-own-LLM 🚀

Greg Richardson

17,992 Aufrufe • vor 1 Jahr

See how the Box MCP server turns Box into a LLM-ready toolbox. In this demo, we showcase Cursor to fast track AI-powered content workflows.
6:56

See how the Box MCP server turns Box into a LLM-ready toolbox. In this demo, we showcase Cursor to fast track AI-powered content workflows.

Box

292,770 Aufrufe • vor 1 Jahr

We've built the best in house observability for Stagehand 🔭 Get inference time, token usage, LLM output, and more on the new dashboard. No more black box, see everything behind the scenes. See for yourself, get started with npx create-browser-app 🤘
0:30

We've built the best in house observability for Stagehand 🔭 Get inference time, token usage, LLM output, and more on the new dashboard. No more black box, see everything behind the scenes. See for yourself, get started with npx create-browser-app 🤘

Stagehand

10,887 Aufrufe • vor 1 Jahr

Stories have shapes: a comedy rises toward joy; a tragedy falls into loss. Inside an LLM, that’s visible more literally: as an LLM reads a story, its internal activations trace a wandering path that reflects the model’s sense of what kind of story it is reading. (1/5)
0:31

Stories have shapes: a comedy rises toward joy; a tragedy falls into loss. Inside an LLM, that’s visible more literally: as an LLM reads a story, its internal activations trace a wandering path that reflects the model’s sense of what kind of story it is reading. (1/5)

Goodfire

105,529 Aufrufe • vor 3 Monaten

Second place: Ambien by give me a sec A daydreaming agent running inside Hermes Agent that samples a curated Obsidian corpus for resonant idea collisions and synthesizes them into published essays, leveraging the harness for iterative voice calibration that keeps the prose from reading like an LLM.
1:18

Second place: Ambien by give me a sec A daydreaming agent running inside Hermes Agent that samples a curated Obsidian corpus for resonant idea collisions and synthesizes them into published essays, leveraging the harness for iterative voice calibration that keeps the prose from reading like an LLM.

Nous Research

26,904 Aufrufe • vor 5 Monaten

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.
36:05

He is 17 sold an LLM system to Anthropic for $2.2M - and at Stanford shared how to build and sell one from scratch: 00:20 - how to build an LLM system that Anthropic will buy for millions 08:34 - one prompt in Opus 5 and the LLM system is ready to sell in 60 minutes 23:47 - how to sell an LLM to Anthropic at 17 with no experience and reach $2.2M a year after watching I built my first LLM system in 60 minutes - and sold it to Anthropic for $120k. save & watch - the article below is one file that builds an LLM system and sells it to Anthropic for $2.2M.

Noisy

25,571 Aufrufe • vor 1 Monat

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!
0:51

Jupyter Agents - LLMs running data analysis directly in a notebook! The agent can load data, execute code, plot results and following your guidance and ideas! A very natural way to collaborate with an LLM over data and it's just scratching the surface of what's possible soon!

Leandro von Werra

200,291 Aufrufe • vor 1 Jahr

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below
0:23

i'm a little sick of chatgpt giving me obviously broken code i've found a "micro agent" approach to LLM code generation can work much better the LLM first generates a *test*, and then enters a loop where it generates and iterates on the code until the tests pass source below

Steve (Builder.io)

544,371 Aufrufe • vor 2 Jahren