Darrell Stone

This new release of GStack is for all the haters on Product Hunt who said it was just a bunch of markdown files

you can instantly 10x your vibecoded frontends by just learning what different ui components are called ofc opus is creating generic slop, the only words you know are menu and button.

Figma CEO Dylan Field just identified the only competitive advantage that AI cannot commoditize. It isn’t your technical skill. It isn’t your speed. It isn’t your tools. Field: “If an agent can do it for you, an agent can do it for someone else.” That’s the fatal flaw in the entire AI productivity argument nobody wants to say out loud. When execution becomes free, execution becomes worthless. The moment anyone can build anything by typing a prompt, the output stops being the differentiator. What remains is taste. The one thing the agent cannot generate for you. Field: “What is different about your setup than others?” If you are typing generic prompts and accepting the first output the agent hands you, you aren’t building a product. You are retrieving a commodity. The same commodity available to every competitor on earth. Field: “You at least have to have something different there in order to not think that you’re just gonna get the same out.” But taste alone isn’t enough. The other half is exploration. Field: “The more you can sample the possibility space, it gives you something to react to.” The blank page is gone. The new constraint isn’t creation. It’s selection. The agent generates hundreds of possibilities in seconds. Your job is to go wide enough to find the best one hiding inside all of them. And then be honest enough with yourself to know when none of them are good enough. Field: “If you find areas where you’re going, ‘Hey, I don’t feel like I am liking this enough,’ then you got to keep pushing.” The creators who win this era won’t be the fastest builders. They’ll be the harshest critics. The ones who can generate the widest possibility space and identify the single best solution inside it. The ones whose taste is specific enough, developed enough, and honest enough to reject everything the agent produces until it produces something worth keeping. The AI can build anything you can describe. It cannot want anything. It cannot feel when something is wrong. It cannot tell the difference between good and extraordinary. That gap is the only moat left.

Engineers-turned-PMs keep making the same psychological error in stakeholder meetings. They assume corporate environments reward merit the same way engineering teams do. After stumbling over and then studying this pattern for a while, I've identified the core disconnect that nobody discusses:

At best, smoking weed kills your motivation and makes you an unproductive dullard. At worst it triggers psychosis and schizophrenia. Decriminalizing was of the worst public health decisions of the last few decades

Some dudes wake Up thinkin bout sleep score numbers truth is you can just wake up and choose to have the best day ever

consumer apps can hit $20,000/month, run at ~95% margins, have zero employees, be built in a weekend with vibe coding, and grow entirely through 100s of ai automated Instagram/tiktok accounts (faceless or avatars) i don’t know a single other business model that lets you do this.

Corollary: as users get Claude Code pilled, they won't automate UIs. They will push work down the stack until they hit something agents can operate on directly with code. Take a risk or finance org: if today's workflow requires dropping a pdf into a Drive, clicking around Google tabs, checking a policy doc, clicking in a Retool, they won't automate those very human steps. They will replace the workflow entirely and redefine it in a lower abstraction layer. PDFs + UIs + click-heavy workflows will move into python, SQL, and APIs.