Secção da base de dados · 12 registros
Pesquisa
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
Notas de campo
Uma dúzia de PDFs sustenta um trilhão de dólares em infraestrutura. São os artigos onde as ideias apareceram pela primeira vez — a maioria é surpreendentemente acessível, e cada registro aqui diz o que importou, sem a matemática.
Comece por estes três
AI
Attention Is All You Need (2017)
Oito autores, uma arquitetura, tudo desde então.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
A correção que mudou a forma como todo modelo é treinado.
DR
DeepSeek-R1 — Reasoning via RL (2025)
A receita aberta para raciocínio — publicada enquanto os rivais mantinham a sua em segredo.
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.