Veritabanı bölümü · 12 kayıtlar
Araştırma
The papers the modern stack is built on — from the transformer to scaling laws, RLHF and reasoning models.
Saha notları
Bir düzine PDF, bir trilyon dolarlık altyapının temelini oluşturuyor. Fikirlerin ilk ortaya çıktığı makaleler bunlar — çoğu şaşırtıcı biçimde okunabilir; buradaki her kayıt matematiğe girmeden neyin önemli olduğunu anlatıyor.
Bu üçle başlayın
AI
Attention Is All You Need (2017)
Sekiz yazar, bir mimari, o günden bu yana her şey.
TC
Training Compute-Optimal LLMs — Chinchilla (2022)
Her modelin eğitilme biçimini değiştiren düzeltme.
DR
DeepSeek-R1 — Reasoning via RL (2025)
Akıl yürütme için açık tarif — rakipler kendi tariflerini gizli tutarken yayımlandı.
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.