Sección de la base de datos · 12 registros
Investigación
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
Notas de campo
Una docena de PDFs sustentan un billón de dólares de infraestructura. Estos son los artículos donde las ideas aparecieron por primera vez — la mayoría son sorprendentemente accesibles, y cada registro aquí le dice qué importó sin las matemáticas.
Empiece por estos tres
AI
Attention Is All You Need (2017)
Ocho autores, una arquitectura, todo lo que vino después.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
La corrección que cambió cómo se entrena cada modelo.
DR
DeepSeek-R1 — Reasoning via RL (2025)
La receta abierta para el razonamiento — publicada mientras los competidores guardaban la suya en secreto.
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.