Datenbankbereich · 12 Datensätze
Recherche
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
Feldnotizen
Ein Dutzend PDFs stützen Infrastruktur im Billionenwert. Das sind die Paper, in denen die Ideen zuerst erschienen – die meisten sind überraschend lesbar, und jeder Eintrag hier erklärt, was wichtig war, ohne die Mathematik.
Mit diesen drei beginnen
AI
Attention Is All You Need (2017)
Acht Autoren, eine Architektur, alles Folgende.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
Die Korrektur, die das Training jedes Modells veränderte.
DR
DeepSeek-R1 — Reasoning via RL (2025)
Das offene Rezept für Reasoning – veröffentlicht, während Konkurrenten ihres geheim hielten.
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.