Sublime

People talk about how AI is going to make design obsolete, and/or make pixel perfect designs not be a thing anymore. I don't think so. Pixel-perfect design mostly existed in designers’ minds anyway. The mocks might perfect but the final product rarely was. Most of the time,

Prompting tip to make Cursor's new MAX mode significantly more effective and reliable: Make sure thinking is turned on. Start by clearly stating your goal. End your prompt with: "But before we start, I want you to fully explore and understand the existing codebase. Don't write

Forget vibe coding. It's time for Chaos Coding: -> Prompt Claude 3.7 Sonnet with your vague idea. -> Say "keep going" repeatedly. -> Watch an incredible product appear from utter chaos. -> Pretend you're still in control. Lean into Sonnet's insanity ... See more

Steal this o3 prompt: Drop your business info into it, and it'll instantly map your competitors and hand you a ranked, actionable list of growth moves you’re not doing yet. -- <instructions> You are a top-tier strategy consultant with deep expertise in competitive analysi... See more

said this to a friend but it applies to many: i think you have a good guess what you should be doing. no need to overthink it! just execute on your inkling for 3 months, and then evaluate if you want to try something diff. course correct more often than that eats your bandwidth

I talked to a friend who wants to start a blog and wanted some advice on that—how to find her voice and so on. A few random thoughts:

Increasingly believe that the "good, cheap, fast—choose two" maxim is devious misinformation spread by the slow. In my experience, "slow" and "expensive" usually go together. I was in a meeting yesterday where lopping a year off a project schedule also ended up reducing the cost substantially. Fundamentally, it takes ti... See more

@shreyas IMO the best product will stem from a very strong mental model of the domain and the users. UXR can help you *get* to such a model, and validate it along the way, but it's important to view the syllogism as UXR -> model -> product, not UXR -> product.