🧠 AI & Machine Learning
22 min read
Deep dives
Long-form engineering thinking.
Essays with 5+ minutes reading time that reward close reading.
🔍
Topic:
Showing 9 of 9 essays
🧠 AI & Machine Learning
10 min read
Jev and the Return of the Smart If Statement
TypeSafe AI's Jev does not want to write your email, explain quantum mechanics or generate an application. It wants to answer a smaller question quickly: given this state, which bounded decision should software make next?
🦀 Rust
7 min read
Memory Is the Budget: Why Rust Gained Popularity in the AI Era
Why Rust won AI infrastructure: its ownership model, zero-cost abstractions, and precise memory layout control eliminate GC pauses and wasted bandwidth - exactly what matters when cost per token is a memory problem, not a compute one
🧠 AI & Machine Learning
7 min read
From Traces to Tests: Closing the Continuous Improvement Loop for AI Agents
A practical loop for keeping AI agent evals fresh: capture production traces with outcome labels, curate the failures worth testing, convert them into property-based eval cases, and verify fixes against both evals and production failure rates.
🧠 AI & Machine Learning
7 min read
AI Search Is Moving Work Out of the Request Path
Retrieve-for-Train suggests a practical design shift: learn repeatable search behavior offline, but keep live facts and permissions online.
🧠 AI & Machine Learning
7 min read
Your AI Agent Needs a Memory Policy, Not Just a Vector Database
Persistent memory is becoming an infrastructure feature. The harder problem is deciding what an agent may remember, trust, update, and forget.
🤖 AI Engineering
7 min read
AI Engineering Is Reliability Engineering for Probabilistic Systems
An LLM demo can be built in an afternoon. A system that uses an LLM safely, economically and repeatedly under production traffic is a different discipline.
🗄️ Databases & Storage
6 min read
Stop Guessing Disk: An Observability-Driven Approach to Cloud Storage for Stateful Workloads
Stop over-provisioning cloud block storage on guesswork: watch queue depth, p99 latency, and burst balance to tell whether you're IOPS-, throughput-, or capacity-bound, then scale only the knob that's actually throttling with the cost math to prove it.
🧠 AI & Machine Learning
6 min read
Before You Build a Custom ML Model, Prove You Need One
A practical framework for deciding when off-the-shelf models have reached their limit—and when your data, economics, and constraints justify building your own.