Geoffrey Litt’s Insightful Perspectives

Honghao Wang

— 1 min read

Code Like a Surgeon: A Smarter Way to Work With AI

A lot of people suggest that AI will transform us into “managers” or “editors”—overseeing, reviewing, and guiding automated work.

But I believe this is an incomplete and potentially misleading view.

Instead, I aim to code like a surgeon.

---

Why a Surgeon Is the Right Model

A surgeon is not a manager.

They still perform highly skilled, critical work—but they rely on a support team to handle preparation, secondary tasks, and administrative steps.

This allows them to focus exclusively on the parts only they can do well.

---

Delegating the Right Tasks to AI

Many secondary tasks can now be handled competently by AI agents.

Here are some I frequently delegate:

  • Guide creation – Before tackling a big task, produce documentation or a guide to relevant parts of the codebase.
  • Code spikes – Have AI prepare an initial attempt or rough sketch for a major change. Even if it’s not production-ready, the ideas shape my next steps.
  • TypeScript fixes & bug resolution – Provide a clear specification and let AI handle the error fixing.
  • Documentation writing – Let AI draft explanatory docs for whatever I’m currently building.

---

Running AI Support in the Background

I often trigger these tasks asynchronously—

while I’m:

  • Taking a lunch break
  • Working on another project
  • Even overnight

When I begin a coding session, I want to feel like a surgeon walking into a prepped operating room: everything ready so I can dive straight into my core work.

---

Scaling With Modern AI Platforms

This approach becomes even more powerful when integrated with modern AI ecosystems.

For instance, platforms like AiToEarn官网 enable:

  • Multi-channel content/code generation
  • Publishing and analytics tracking
  • Efficient monetization of results

With tools like this, your “AI support team” can handle more than just code—it can amplify your output and impact worldwide.

---

Bottom line: Treat AI as your skilled surgical support team, and you’ll stay focused on the high-value work only you can do.

---

Do you want me to also expand this into a structured “Surgeon’s Workflow with AI” guide so your readers can immediately adopt the method? That would make it even more actionable.

Read more

NeurIPS 2025 | ARGRE Framework Enables Efficient LLM Detox: Autoregressive Reward Guidance for Faster, More Accurate, and Lighter Safety Alignment

NeurIPS 2025 | ARGRE Framework Enables Efficient LLM Detox: Autoregressive Reward Guidance for Faster, More Accurate, and Lighter Safety Alignment

2025-10-25 12:24 Beijing A New Method for Safe LLM Deployment: Fast, Accurate, and Lightweight Large Language Models (LLMs) are widely used in content creation, enterprise services, and many other domains. However, content safety—including risks such as hate speech, discrimination, and threats—remains a major challenge for real-world deployment.

By Honghao Wang