I’ve not posted in a while, so I thought I’d share one of the short stories I’ve been working on. Hope you like it!

Generalisation in deep learning asks the question of “how well will my AI/deep learning model do in the wild?”, or, “how much did my model actually learn about the real world, rather than just about the data it was trained on?”

Scaling laws are empirical formulae that relate two or more measurable quantities of a system. In deep learning, “scaling law” most commonly refers to the relationship between the amount of data and computation (model capacity) we put into a training run, vs. the generalisation error we get on some held-out test data.

Today I’ve decided to talk about the vacuum catastrophe, a.k.a. the cosmological constant problem, a.k.a. “the worst theoretical prediction in the history of physics”.

A “stochastic parrot” is, according to some, a machine that can produce convincing-sounding text without ever truly understanding the meaning of what they write. I can relate.

So I couldn’t resist getting a subscription to Claude 3 Opus, Anthropic’s latest chatbot. Here’s what I think so far.

Wavefunction collapse is loosely defined as the point at which a “quantum” system becomes a “classical” one. But what does that mean?

Although I’m a bit late to the party on this one, I thought today would be a good day to write about Sora. This will be a longer post so try not to nod off.

This is my second ever post. Today I’ve decided to write about a fascinating and puzzling formula from the world of physics.

Hello, world!