I ve noticed that my workflow has changed completely over the last year. I rarely start a new project with a blank file anymore. Instead, I pick a template, reuse snippets, or let an AI helper suggest the structure and then I just vibe my way through the build.

It s faster, but sometimes I miss the old blank screen energy, when every line felt handcrafted.

I m curious how others here approach it:

Do you still prefer to build from scratch?

ChatGPT now has 800M+ weekly active users and processes 2.5 billion prompts per day. It's the 6th most visited website globally.

Perplexity, Claude, Gemini - they're all growing fast too.

What I'm curious about: Are any of you actually seeing customers/signups coming from these platforms?

Like, are people asking ChatGPT "what's the best [your category]" and then actually finding their way to your product?

It s easy to measure latency or accuracy.

But the real costs often hide in the background- compute burn, idle tokens, redundant calls, or that temporary caching fix that quietly eats your budget.

I keep seeing advice like use this model for the easy stuff and that one for complex problems. But it makes me wonder what really counts as a complex problem for an LLM?

For us, complex usually means lots of steps, deep reasoning, or tricky knowledge. But for AI, the definition might be different. Some things that feel easy for us can be surprisingly hard for models, while things that seem tough for us (like scanning huge datasets quickly) might be trivial for them.

Supabase recently surveyed over 2,000 startup founders and builders to uncover what's powering modern startups: tech stacks, GTM, and approach to AI.

See full report here

The other day on LinkedIn, I came across a competitor in my space. The founder proudly wrote in their bio: "Built the tool from idea to launch in just 2 weeks."

My first thought: wow that is really fast.

My second thought: wait, how??

So naturally, I signed up to try it.

Hello everyone, I am dabbling in "Vibe Coding" and wanted to know if anyone has any advice or best practices?
I have used Cursor for a while, but have just started to use Claude Code to take a more hands-off approach. I am liking it so far for getting the general layout and functionality, and then I go in to clean up and finish the work. I have also used some MCPs, but I am looking for more!
All advice is appreciated. Thanks in advance!

I m a PM, and I ve been prototyping more and more in Lovable/V0 lately it s quickly becoming my default sketchpad for product ideas.
One challenge I keep running into when sharing with stakeholders: how to present different variations of the same prototype.
It feels like today s vibecoding tools don t yet have the equivalent of feature flags, a simple way to toggle between ideas within one prototype.
I m curious how others approach this. Do you fork? Keep multiple versions and restore as needed? Or is there another workflow I should try?

Vibe coding tools have been making huge improvements, but things can always get better.

What blockers are you still running into? What has no one solved yet? What do you wish you could do, but can't yet?