Field notes

The AI Ascend blog.

Deep dives, applied tutorials, and the AI news that matters.

May 31, 2026

How Much Data Is Enough? The Chinchilla Correction

For years the field raced to build bigger models. Then a 2022 study showed most of those giants were undertrained, and quietly redrew the map of how to spend a compute budget.

3 min read

May 31, 2026

The Length of a Thought: Why Context Windows Became the New Battleground

A 512-token model could read a paragraph. A million-token model can read a novel. The journey between those two numbers is a story about quadratic cost, clever approximations, and what it means for a machine to "remember."

4 min read

May 30, 2026

Why 'agents' is the wrong frame for most workflows you actually want

The industry frames every LLM feature as an agent. Most production systems that work are pipelines with one or two LLM steps and clear handoffs. Default to a workflow, reach for an agent only when the problem demands it.

10 min read

May 30, 2026

RLHF vs DPO in production: what we learned shipping both

DPO is the right default for almost every preference-tuning project in 2026, but the cases where PPO still wins are sharper and more common than the simplicity pitch admits.

9 min read

May 30, 2026

The $8M trillion: when frontier-grade training falls out of the lab

DeepSeek shipped a 1.6T-parameter model in April 2026 with native Ascend inference support while OpenAI committed $500B to Stargate. Both can be right, but only one of them is a moat.

9 min read

May 29, 2026

Stop fine-tuning for facts: the silent productivity tax of mis-matched tools

Most teams reach for fine-tuning when they should reach for retrieval. The cost is not just dollars - it is months of confused engineers trying to figure out why the model started lying again.

3 min read

May 24, 2026 · ✦ co-written with Claude

Prompt Caching: A Practical Guide for Production LLM Engineering

Prompt Caching is one of the highest-leverage optimizations available to you

5 min read