SSCI / THE READING ROOM
AI guides & practical tools
Background reading for the news: understand systems, examine evidence and plan local inference.
AI agents explained: tools, workflows and evaluation →
What makes an AI system an agent? Understand the tool-use loop, compare agents with workflows, and evaluate reliability before deployment.
Open weights vs open source AI: what is the difference? →Downloadable weights are only part of the picture. Compare model access, license rights, training information and practical deployment requirements.
How to read an AI research paper beyond the headline →A practical reading checklist for AI papers: examine the claim, data, baseline, evaluation budget, uncertainty and reproducibility.
LLM memory calculator: weights, KV cache and VRAM →Estimate local LLM inference memory from parameter count, quantization, context length and KV-cache layout. See the formula and its limitations.