Essay Jul 2026

What changes when a Model can ReAct

How agentic behavior changes the workload shape: one request becomes many model calls, tool invocations, observations, and decisions that need orchestration around the model.

Essay Jul 2026

You control more of the bill than you think

Four practical levers for inference cost control, from routing and prompt shape to model choice and system design, beyond the headline token price.

Essay Jun 2026

Why Token Price Isn't the Whole Cost

Why inference cost is not just token pricing: latency, throughput, retries, context length, model choice, and system overhead all shape what AI actually costs to run.

Essay Jun 2026

Knowing Whether the Model Actually Works

A practical look at evaluation: building task-specific checks, choosing useful datasets, and measuring model changes against the production behavior that actually matters.

Essay Jun 2026

Post-training is the new Pretraining

A freshly pretrained model is not completely useful to talk to. This essay walks through supervised fine-tuning, preference optimization, and reasoning RL.

Essay Jun 2026

Prompt, Retrieve, Fine-Tune, Distill - In that order

A practical ladder for improving AI systems: start with prompting, move to retrieval when context is missing, fine-tune when behavior must shift, and distill when smaller models need to inherit capability.

Essay May 2026

How Models Learn (It's Simpler Than You Think)

A clear starting point for pretraining: how models learn patterns from massive text corpora, why next-token prediction scales into useful capability, and where infrastructure bottlenecks start to matter.

Essay May 2026

A GPU Cluster isn't a Cluster of GPUs

A thousand-GPU cluster is more than chips. The real system includes HBM, interconnect, networking, storage, power, cooling, and scheduling choices that determine whether accelerators stay fed.

Essay May 2026

Chip Is the Easy Part

Why comparing AI chips by spec sheets misses the larger architecture question: the best accelerator depends on software maturity, memory behavior, workload shape, and the system around the silicon.

Essay May 2026

Not all "AI Chips" do the same thing

A tour through AI chip families and the trade-offs each one makes against compute, memory capacity, and memory bandwidth.

Essay May 2026

Why I Stopped Thinking About AI Infrastructure as "Just GPUs"

AI infrastructure has evolved past stacking GPUs. Success means balancing accelerators for tensor math, CPUs for orchestration logic, and DPUs for networking.