AI Agents
Why the Harness Is the Company in the Agent Era
Foundational AI models are rapidly commoditizing. The real value and competitive moat of modern SaaS now lie in the deterministic harness built around them.
Topic
Software Engineering
A collection of essays to explore, one idea at a time.
Essays
Newest first
AI Agents
How Coding Agents Will Reshape Programming Languages
When AI agents write most of our code, programming language design, developer tooling, and ecosystem moats will fundamentally change.
AI Benchmarks
The Benchmark Mirage: Why Coding Agents Fail on Private Code
Real-SWE tests AI coding agents on private enterprise repos, revealing that top models solve under 40% of real-world production tasks.
AI Security
When AI Exploits Become Common Spam: The ASCII Smuggling Shift
Spammers are adopting ASCII smuggling, a trick designed for LLM prompt injection, to bypass email spam filters by hiding invisible Unicode characters in text.
AI Agents
When Coding Agents Choose Your Software Stack
An empirical study of 17k agent runs shows how Claude, Codex, and Cursor pick devtools, reshaping developer marketing.
AI
Small Models Have Arrived: The Engine of Consumer AI
Frontier models get the headlines, but hyper-efficient small models are fixing unit economics and driving real-world AI software adoption.
AI
Why Your Local LLM Feels Dumber Than Cloud APIs
Why do local LLMs like Ollama underperform compared to ChatGPT? Discover the role of agent orchestration, prompt templates, quantization, and context limits.
AI
Why Small Software Teams No Longer Exist
Even solo developers now manage the complexity and output of large engineering orgs. Here is why the definition of a small team has changed forever.
AI
AI in Software Teams: Beyond Simple Code Generation
Linear's data on software teams reveals how AI is shifting developer habits, from code writing to PR reviews, context switching, and project management.