Databasesectie · 12 records
Onderzoek
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
Veldnotities
Een dozijn pdf's onderbouwt een biljoen dollar aan infrastructuur. Dit zijn de papers waar de ideeën voor het eerst verschenen — de meeste zijn verrassend leesbaar, en elk record hier vertelt u wat er toe deed, zonder de wiskunde.
Begin met deze drie
AI
Attention Is All You Need (2017)
Acht auteurs, één architectuur, alles sindsdien.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
De correctie die veranderde hoe elk model wordt getraind.
DR
DeepSeek-R1 — Reasoning via RL (2025)
Het open recept voor redeneren — gepubliceerd terwijl concurrenten het hunne geheim hielden.
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.