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.
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