Tag Archives: web

AI, webdev

8 Top Tips to Actually Use Cursor (Without Setting Your Wallet on Fire)

If you’ve been coding anytime in the past year, you’ve probably heard the buzz about Cursor — the AI-powered IDE that promises to write your code, clean your code, and maybe even refactor your soul.

It’s built on top of VS Code, so it feels instantly familiar.
But the moment you hit that shiny AI shortcut, you realize: this thing is smarter than your codebase and hungrier than your wallet.

After a few months of using Cursor — and after accidentally vaporizing a scandalous number of API tokens — I’ve learned how to stay productive and solvent.
And yes, the TL;DR is that you can still combine Cursor with Ollama + local models to get many of these benefits for free.
Here are my 8 hard-earned tips to make Cursor your loyal sidekick within the limits of your budget.

The #1 tip: Control context scope aggressively – This is the biggest win

Cursor auto-includes files, diffs, and history—this explodes token usage.

Do this:

  • Manually select only the exact files/functions needed
  • Avoid “entire repo” context unless absolutely required
  • Use @file and @selection instead of implicit context
  • Clear chat or start a new thread when switching tasks

Why it matters:
Token cost scales with every line in context, not just your prompt.

Below are a bit more tips:

Continue reading →
Standard
Chrome

High Conversion Web Forms

Cam and Ido - web forms course lead image

Last week, my new course “Building High Conversion Web Forms” was launch on Udacity. I had the pleasure to work with Cameron Pittman on this course and I hope you are going to like the outcome.

Let’s take one (I promise not two) step back, and think about forms. If you think on any meaningful experience on the web today, you will find out that it comes with a form. It might be a shopping cart, registration form, survey or even every login form. If it’s valuable, most probably it got a box that wish someone will fill it with information. Whether it’s a form made of text boxes, toggles, buttons, checkboxes, or touchable widgets, web developers need to be purposeful about forms to make users happy and increase conversions.

In our course, you’ll learn best practices for modern forms. It’s not just ‘watching’ videos. You’ll practice your skills along the way with a few self-directed projects, including an e-commerce checkout and an event planner app! As a special bonus, you’ll also watch a series of interviews with Luke Wroblewski, Google Product Director.

Continue reading →

Standard
Chrome, JavaScript, mobile, webdev

Physical Web On Mobile

Physical Web is the new approach to unleash the core superpower of the web: interaction on demand.
People should be able to walk up to any smart device, think on classic cases like: a vending machine, an art item, a poster, a toy, a bus stop, a rental car – and not have to download an app first. They should be able to just tap and interact with them.

forest in the morning

The Physical Web is not shipping yet nor is it a Google product. This is an early-stage experimental project and we’re developing it out in the open as we do all things related to the web. This should only be of interest to developers looking to test out this feature and provide feedback. The Physical Web is an effort to extend the core superpower of the web – the URL – to everyday physical objects. The user experience of smart objects should be much like links in a web browser: i.e., just tap and use. At its base, the Physical Web is a discovery service: a smart object broadcasts relevant URLs that any nearby device can receive.
This simple capability can unlock exciting new ways to interact with the Web. Continue reading →

Standard
Business, Chrome, cloud

2014 Summary

2014-5-new-year

2014 was a busy year.
In few moments of reflection, it feels more like 3-4 years. Anyway, let’s try to see where was the interesting stuff on this blog.

The Web

 google think cloud

Continue reading →

Standard