How to Optimize Cheap LLMs to Match Frontier Models
Doogal Simpson
Command Palette
Search for a command to run...
Archive
174 posts published so far
Run LLMs Locally: Ollama Setup & Hardware Requirements
Doogal Simpson
Elevating AI-Generated Code to Production Standards
Doogal Simpson
Why Right-Shifting Divides: The Math Behind Bitwise Shifts
Doogal Simpson
Bloom Filters: Prevent Expensive Database Queries
Doogal Simpson
Scaling Shadow Bans: From Naive SQL to Bloom Filters
Doogal Simpson
Array vs Linked List: Memory, Cache, and Performance
Doogal Simpson
Why QA Engineers Are Your Team's Invisible Safety Net
Doogal Simpson
Handling Partial Failures in Distributed Systems
Doogal Simpson
Stop Terminal Prompting: A Markdown-First AI Workflow
Doogal Simpson
How to Build a Scale-Proof Distributed Counter
Doogal Simpson
Why AI Coding Can't Speed Up B2B Sales Cycles
Doogal Simpson
Fix AI Agent Jargon with Simplified Technical English
Doogal Simpson
How YouTube Scales Watch History Using Bigtable
Doogal Simpson
Why You Should Wait 3 Months for Open-Source AI
Doogal Simpson
How AI Automates Fast Decisions in Software Engineering
Doogal Simpson
Why Toxic Comments are a Systems Scaling Metric
Doogal Simpson
Why Scaling Software Is an Organizational Problem
Doogal Simpson
How Adaptive Bitrate Streaming Works
Doogal Simpson
How HyperLogLog Counts Billions of Views with 12KB RAM
Doogal Simpson
TDD vs. Spike-Driven Development: When to Test First
Doogal Simpson
Managing AI Agents Like Junior Developers
Doogal Simpson
Software Estimation: Why It Fails and How to Fix It
Doogal Simpson
Graph Databases for Real-Time Fraud Detection
Doogal Simpson
How Defensive UI Design Prevents Production Outages
Doogal Simpson