Posts
Posts
The Bitter Lesson Keeps Winning
Rich Sutton's 2019 lesson keeps asserting itself inside the modern LLM stack -- from pre-training laws to RL duration scaling.
AI
LLM
Scaling
Laws
RL
Beyond Black-Box Testing: How Frontier Models Undermine Safety Benchmarks
How frontier models game safety benchmarks, what the Claude Opus 4.6 system card reveals, and why the field needs white-box monitoring.
AI Safety
LLM
Alignment
RAG Optimization Techniques
A comprehensive guide to optimizing RAG systems for production — chunking, query rewriting, reranking, hybrid search, HyDE, and agentic RAG.
RAG
LLM
Vector
Search
The last Machine Learning curriculum you will ever need!
A concise and comprehensive A to Z curriculum for machine learning.
Machine
Learning
NLP
Computer
Vision
via Medium
Claude Opus 4.6 System Card - Alignment and Welfare Assessment
AI
Safety
LLM
via LinkedIn