Database section · 12 records
Research
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
Field notes
A dozen PDFs underpin a trillion dollars of infrastructure. These are the papers where the ideas first appeared — most are surprisingly readable, and each record here tells you what mattered without the math.
Start with these three
AI
Attention Is All You Need (2017)
Eight authors, one architecture, everything since.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
The correction that changed how every model is trained.
DR
DeepSeek-R1 — Reasoning via RL (2025)
The open recipe for reasoning — published while rivals kept theirs secret.
Foundational papers
12
AI
Attention Is All You Need (2017)
The eight Google authors who invented the transformer.
A(
AlexNet (2012)
The ImageNet result that started the deep-learning era — on two gaming GPUs.
CA
Constitutional AI (2022)
Anthropic's method: models critique themselves against written principles.
DR
DeepSeek-R1 — Reasoning via RL (2025)
The open recipe for reasoning models — a Nature cover, from a hedge fund's lab.
DD
Denoising Diffusion Probabilistic Models (2020)
The DDPM paper behind every image and video generator.
F(
FlashAttention (2022)
The kernel trick that made long context affordable.
HA
Highly Accurate Protein Structure Prediction (2021)
AlphaFold 2 in Nature — the result that won a Nobel.
I—
InstructGPT — RLHF at Scale (2022)
How raw language models became assistants people can use.
LM
Language Models are Few-Shot Learners (2020)
The GPT-3 paper: capability from scale, tasks from prompts.
LL
LoRA: Low-Rank Adaptation (2021)
Fine-tuning for the GPU-poor — tiny adapters instead of full weights.
SL
Scaling Laws for Neural Language Models (2020)
Kaplan et al.: loss falls as a power law in compute — the investment thesis, quantified.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
DeepMind's correction: most models were undertrained on data.