데이터베이스 섹션 · 12 레코드
리서치
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
현장 노트
수십 편의 PDF가 수조 달러 규모 인프라의 토대를 이룬다. 이것이 아이디어가 처음 등장한 논문들이다 — 대부분 놀랍도록 읽기 쉬우며, 각 기록은 수식 없이 무엇이 중요했는지를 알려준다.
이 세 가지부터 시작하세요
AI
Attention Is All You Need (2017)
저자 여덟 명, 아키텍처 하나, 그 이후의 모든 것.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
모든 모델의 훈련 방식을 바꾼 수정.
DR
DeepSeek-R1 — Reasoning via RL (2025)
공개된 추론의 레시피 — 경쟁사들이 비밀로 유지하는 동안 공개됨.
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.