Way Enough

You’re not even trying to be clever. You’re just solving tiny problems. Making the machine do what it should have done in the first place. And then something happens. You cross a threshold. You look at your tools, your environment, your operating system—even your editor—and suddenly everything is fair game.

This fear of 'wasting' a meal, or an entire trip, ironically leads people to create exactly what they're trying to avoid, not literally wasted experiences, but stressful, anxious, and ultimately unfulfilling vacations, where you run around trying to maximize so much, you miss the part where you stop, relax, take stuff in, and live.

To that end, I never use ChatGPT.com or other normal-person frontends for accessing LLMs because they are harder to control. Instead, I typically access the backend UIs provided by each LLM service, which serve as a light wrapper over the API functionality which also makes it easy to port to code if necessary.

The tooling that most software developers use day-to-day hides context windows from the user and encourages endless chatops sessions within the same context window, even if the current task is unrelated to the previous task.This creates bad outcomes because what is loaded into memory is unrelated to the job to be done, and results in noise from software engineers saying that 'AI doesn't work', but in reality, it's how the software engineers are holding/using the tool that's at fault.

With all that context loaded into the window, all that data is now available for consideration when you ask a question. Thus, there's a probability that it'll generate a news article about Meerkats wearing party hats in response to a search for Meerkat facts (ie. Wikipedia). That might sound obvious, but it's not. The tooling that most software developers use day-to-day hides context windows from the user and encourages endless chatops sessions within the same context window, even if the current task is unrelated to the previous task. This creates bad outcomes because what is loaded into memory is unrelated to the job to be done, and results in noise from software engineers saying that 'AI doesn't work', but in reality, it's how the software engineers are holding/using the tool that's at fault. My #1 recommendation for people these days is to use a context window for one task, and one task only. If your coding agent is misbehaving, it's time to create a new context window. If the bowling ball is in the gutter, there's no saving it. It's in the gutter.

But building a small and yet highly impressive agent doesn’t even require that. You can do it in less than 400 lines of code, most of which is boilerplate.

There's something cooked about Windsurf/Cursors' go-to-market pricing - there's no way they are turning a profit at $50/month. $50/month gets you a happy meal experience. If you want more power, you gotta ditch snacking at McDonald’s.

Going forward, companies should budget $100 USD to $500 USD per day, per dev, on tokens as the new normal for business, which is circa $25k USD (low end) to $50k USD (likely) to $127k USD (highest) per year.

But the issue that they will inevitably run into with Windsurf is that GPT just isn't the best in class for programming. Everyone who's using Windsurf is almost definitely using Claude or Gemini. Even though the "GPT wrapper" term was always meant as an insult, it is in practice a huge table stakes feature to be able to wrap around many different LLM providers. That flexibility is what allows a company like Windsurf to ride the machine learning wave, buoyed along by everyone else's investments. Cursor really only took off when Claude suddenly got really good at programming, after all. If Windsurf ends up being tied exclusively to GPT, many of its users may leave the platform simply because it is now a worse platform. But if there isn't any vendor lock in, we're back to square one — what is the point?