Stories from the gateway
Fundamentals
Data Contamination in Training: Why Scores Overstate Skill
How benchmark data leaks into training sets, why it is hard to prove, and what a contaminated score actually costs you when you pick a model for real work.
· 9 min read
AI Agents
Debugging a Stuck Agent: A Triage Runbook
Stuck is four different failures with four different fixes. How to tell hung from looping from stalled from quietly truncated, and what to do about each one.
· 9 min read
Models
DeepSeek V4 Flash vs MiniMax M3: Cheapest Against Multimodal
· 8 min read
Models
DeepSeek V4 Flash vs Qwen 3.6: Rent Cheap or Own It
· 9 min read
Models
DeepSeek V4 Flash: 1M Context at 13B Active Parameters
· 8 min read
Models
DeepSeek V4 Pro vs Qwen 3.6: 1.6T or 27B, for 3 Points
· 9 min read
Models
DeepSeek V4 Pro vs V4 Flash: Same Window, Different Brain
· 8 min readModels
Dense vs Mixture-of-Experts: Which You Can Actually Run
· 9 min read
AI Agents
Dependency-Aware Planning: Ordering Work That Blocks
· 9 min read
Cost & Pricing
Designing an AI Spend Dashboard People Actually Read
· 11 min read
AI Agents
Detecting Agent Loops Before They Burn Your Budget
· 8 min read
Cost & Pricing
Does Streaming Cost More? What You Actually Pay For
· 8 min read
Fundamentals
DPO vs RLHF: Two Routes From Preferences to Model Behaviour
· 9 min read
Guides
Emacs LLM Setup: A Model Endpoint Without the Mouse
· 9 min readReady to start?
Every model, one key. Start free and upgrade when you are ready.