Home on Nathaniel Thomas

Many have caught onto the truth that AGI-through-pure-LLM-scaling is probably not going to happen.

It’s that time of year again.

As we start training LLMs as Agents, we must think about how to best pass information to and from the real-world environment.

I recently bought Bryan Johnson’s Super Veggie T-Shirt, in order to fully immerse myself in his protocol.

Excalidraw currently doesn’t support LATEX, which sucks.

The Sharpe Ratio measures the quality of an equity or hedge fund by showing the return per unit of risk, calculated as σμ−r, where μ is the expected return, r is the risk-free rate, and σ is the standard deviation (volatility).

I find entropy to be extremely fascinating.

I’m doing AoC in Haskell to learn the language.

This entire site is static.

Goal Suppose we have a dataset of features, but no labels.

I am a Neovim diehard, but it is impossible to use over SSH.

Training a deep neural network is essentially a compression task.

This is a method of evaluating strategies for the multi-armed bandit problem 1.

This is a collection of V60 recipes that I have used.

Bayesian Parameter Estimation (BPE) is fundamentally different compared to MLE or MAP.

Goal We are given a dataset D, which contains feature vectors xk and class labels ωk.

The goal is essentially the same as MLE.

Causal self-attention is the mechanism underpinning most of the advances in AI since 2017.

We’re going to go through a minimal example that will let you run Rust code on the client side of a Hugo site.

Explore different methods to win, and beat expert humans in 2048 interactively!

Draw digits on the canvas and watch an AI guess what it is!

One of the most striking elements of Silicon Valley to outsiders is productivity culture.

If you’re a nerd, and you’ve been around Macs for a while, you might remember Applescript.

My previous post (which was honestly created to test out the theme for this site), provided a few code snippets that computed N terms of the sum of inverse squares.

Hello, World!