Notes from someone still learning.

Field notes on AI, machine learning, and whatever I'm trying to understand this week, sorted into boxes so the ideas stay caught.

4 logs

Math Foundations

Vectors, gradients, and the loss functions under it all.
3 logs

Precision & Quantization

Floats, quantization, and FP8 training that does not blow up.
4 logs

GPUs & Hardware

What the silicon, memory, and network are actually doing.
8 logs

Training Systems

Autograd, scaling laws, data pipelines, the loop itself.
13 logs

Clusters & Reliability

Schedulers, collectives, checkpoints, staying up at scale.
7 logs

Transformers & Inference

Attention architectures and the systems that serve them.
3 logs

Evaluation

Measuring whether any of it actually works.
5 logs

Post-Training & Alignment

RLHF, DPO, and GRPO: the reward models and rollout loops that turn a base model into a product.