Vide Coding Day 11, So today’s been a time of introspection and reflection. I have learned a lot becoming a ‘vibe coder’ and it has been addictive. For real. My #1 learning is an old one, re-learned: Building Great Software is Still Hard. Getting going is easier than ever. 🧵

On the dev tools side, I’ve asked all the best CTOs in my portfolio how much they really benefit from Cursor, Claude Code, et. al. The consistent answer: net net, no one is giving back their Claude Code. No one. But net net, alone, it lets folks move about 20%-40% faster. Why? These tools (all really Anthropic LLMs) help everyone do routine work faster, and in fact, some of the best devs I talk to can do 90% of most of their routine work in prompts. But what about the hard stuff? The stuff that hasn’t been done before? The novel stuff? What about the planning? The thinking? What about code reviews and checking the work? That all takes time. So net net many are seeing a 20%-40% real productivity boost from Claude Code et. al. Much higher for routine stuff, but net net of all of the job — that’s where it seems to land today.

On the platform side, the B2C side, Replit+Loveable etc., this tools are magical. Magical. Maybe more than magical. If you want to build a POC or prototype, it’s all magic, really. But in the end, if you want to built true commercial grade apps, then they are … just tools. Flawed tools, magical tools, but tools. At least today. You can now think up an app and see it prototyped in < 20 minutes. Longer if you want all the buttons to work, but still. But getting to >great< software? That’s in its own ways is hard as ever. Even if the tools are so much cooler, faster, and slicker. No great engineers have been made obsolete here.

Honestly I might have gotten a little lost here. I dropped everything for a while. Vibe coded all weekend, first thing in the morning, and more. I was addicted. For real. The software is so, so, so cool. But now I’m slowing it down. And thinking about what it takes to build Great Software. What the tools, planning, timing and more than it takes. And it remains something that requires patience, iteration, testing, and a lot of commitment. And even if you one-shot an app in an hour or day, to do it for real, you have to maintain it for years. If it’s a real app. In real, commercial production.

No one is going to roll their own Salesforce, period. That is a social media myth. If you can buy a piece of >great< software off the shelf, remember it’s a gift. That is still so, so hard to build. And if you can buy it for $5-$200 a month? Just buy that magical software. Where you can’t though? Vibe it. But plan it. Understand it. Scope it. And realize building something great is a long, tough, frustrating, unpredictable road. That even the best tool, the best one, can’t get you to all by itself.

And the good news? All these tools are constantly getting better. Cursor + Windsurf are like a year old. Replit the company has been at it for decade, but the vibe version in 9 months old. Loveable is just as young. And they are iterating at a furious pace. Where they will be in 6-9 months, man. It’s gonna be awesome.

Day 10 here: