Microsoft research reveals new prompt engineering techniques that makes GPT-4 achieve previously impossible performance levels

Unlock GPT-4's potential with new prompt engineering techniques that outperform specialized AI, enhancing performance across various domains.

Microsoft’s research study demonstrates the effectiveness of advanced prompting techniques such as Chain of Thought (CoT) reasoning, dynamic few-shot selection, self-generated chain of thought, and choice shuffle ensembling in causing a generalist AI (GPT-4) to outperform a specialist AI (Med-PaLM 2) that was specifically trained for a given domain. This research paper confirms insights that advanced generative AI users have discovered, and the Medprompt technique has the potential to be used to elicit high quality output in any knowledge area, eliminating the need to intensively train a model on specific domains.

Original article: Researchers Extend GPT-4 With New Prompting Method

Featured writing

Why customer tools are organized wrong

This article reveals a fundamental flaw in how customer support tools are designed—organizing by interaction type instead of by customer—and explains why this fragmentation wastes time and obscures the full picture you need to help users effectively.

Infrastructure shapes thought

The tools you build determine what kinds of thinking become possible. On infrastructure, friction, and building deliberately for thought rather than just throughput.

Server-Side Dashboard Architecture: Why Moving Data Fetching Off the Browser Changes Everything

How choosing server-side rendering solved security, CORS, and credential management problems I didn't know I had.

Books

The Work of Being (in progress)

A book on AI, judgment, and staying human at work.

The Practice of Work (in progress)

Practical essays on how work actually gets done.

Recent writing

We always panic about new tools (and we're always wrong)

Every time a new tool emerges for making or manipulating symbols, we panic. The pattern is so consistent it's almost embarrassing. Here's what happened each time.

Dev reflection - February 03, 2026

I've been thinking about constraints today. Not the kind that block you—the kind that clarify. There's a difference, and most people miss it.

When execution becomes cheap, ideas become expensive

This article reveals a fundamental shift in how organizations operate: as AI makes execution nearly instantaneous, the bottleneck has moved from implementation to decision-making. Understanding this transition is critical for anyone leading teams or making strategic choices in an AI-enabled world.

View all writing →