Sherwin Wu V2

The role of a software engineer is shifting from manual line-by-line coding to high-level orchestration and management of parallel AI agent threads.

"Engineers are becoming tech leads. They're managing fleets and fleets of agents. It literally feels like we're wizards casting all these spells and these spells are kind of like going out and doing th..."

To master AI-driven development, teams must eliminate manual 'escape hatches' and force themselves to solve code issues through model steering alone.

"There's a team that's actually doing an experiment right now within OpenAI where they are maintaining a 100% Codex-written code base. They run into the exact problems that you're describing. And so us..."

As AI dramatically increases code volume, manual review must be augmented with AI-powered automation to maintain quality without becoming a bottleneck.

"100% of our PRs are reviewed by Codex daily as well. So basically any code that goes into production that's merged in, Codex kind of has its eyes on and suggests improvements, suggests changes in the..."

Building complex frameworks to solve current model weaknesses is a losing strategy, as models will eventually absorb that functionality natively.

"The field and the models themselves are just changing so, so quickly. They tend to disrupt themselves. The models will eat your scaffolding for breakfast."

The rise of hyper-efficient micro-startups will create a massive new market for specialized B2B software to power their operations.

"To enable a one person billion dollar startup, there might be a hundred other small startups building bespoke software. So I think we might actually enter into a golden age of B2B SaaS."