Jason Yun

[Lilys.ai @LilysAI_]

Made an interactive note from a @3blue1brown video

[Notion @NotionHQ]

So @_Brian_Zhang built a full-on simulation of The Office using Notion Custom Agents in < 48 hours.

He took 1st place, received 10k+ in credits, then sat down with us to explain how it all worked. We chat about:

> Proximity based reasoning for agents
> Managing long term context windows
> Keeping characters “in character” with reflection loops
> The push/pull between plan mode and reactive decision-making
> What surprised him most

Michael would be proud.

[Jason Yun @junseon0807]

@Brennan_Lup Let’s connect

[Jason Yun @junseon0807]

I turned karpathy's 3hour lecture into an interactive book

[Jason Yun @junseon0807]

masked attention -&gt; interactive visual

[yv @yvbbrjdr]

推荐大家读一下MAI-Thinking-1的technical paper，里面有详细的怎么训出一个SOTA LLM的（几乎）所有细节。

https://t.co/it5mCFd6v3

[Jason Yun @junseon0807]

@yvbbrjdr 我把这篇论文做成了交互式教材~ 用这个来理解就对了!
https://t.co/ca0tPDTvSW

[Jason Yun @junseon0807]

@a16z Here's a summary
https://t.co/Vf5PBRKLVN

[Jason Yun @junseon0807]

@eng_khairallah1 Here's a summary
https://t.co/X8N6sGmr3f

[Jason Yun @junseon0807]

@askalphaxiv interactive summary
https://t.co/swcKcEtZdh

[Jason Yun @junseon0807]

@garrytan skillOpt summary
https://t.co/2dgDVH7Hkh

[Jason Yun @junseon0807]

@omarsar0 paper -&gt; interactive artifact
https://t.co/2dgDVH7Hkh

[Jason Yun @junseon0807]

@BenjDicken Here's a simplified version of Stanford's lecture on Transformers

https://t.co/mmeG9Jor6p

[Jason Yun @junseon0807]

@tfadell summary
https://t.co/3RE3nwbbUp

[Jason Yun @junseon0807]

Here's a summary
https://t.co/bOTLCPzKcR

[Turing Post @TheTuringPost]

A must-read survey to refresh math and gen AI basics → The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer

It shows a clear walkthrough of how gen AI learns to understand, model, and create complex data, covering:

- Latent algebra foundations: PCA, SVD, autoencoders
- Latent models: PPCA and VAEs
- VAEs: ELBO, inference, reparameterization
- Diffusion: the way from noise → denoising
- Score-based and continuous-time generative modelling
- Density models: flows, autoregression
- GANs and energy-based models beyond likelihoods

[Jason Yun @junseon0807]

@developer_quant まとめはこちら。インタラクティブな図解がいい感じです。
@tetumemo

https://t.co/bsNh4OOKs6

[Lilys.ai @LilysAI_]

Someone made a game to explain ReAct agents!!

[Jason Yun @junseon0807]

@DanielMiessler @LilysAI_ summary

[Jason Yun @junseon0807]

@karpathy @readwise save thread