Every generation is blamed for cheating by using tools the previous generation did not have access to.

I remember working in Photoshop and there were no layers. When there was no magnetic lasso. I remember when autocomplete was not a thing in the IDE. I remember when the IDE did not exist, you wrote in notepad. I remember when sampling in music was considered cheating. When using open source was considered unprofessional. When using Wikipedia was cheating. When using stock photos was cheating. When using Stack Overflow was cheating.

I will remember when using GenAI was considered cheating.​​​​​​​​​​​​​​​​

Today I watched the Getting Lost documentary about the awesome tv-series Lost. One interesting fact is that the writers never expected to get past the pilot. They focused on making one episode that worked. But they are experienced writers and by trade they embedded potential in the characters and left small plots that could be picked up.

Like friendly TODOs in code. Not promises to implement. Just honest markers that say “this could be something.” or ”remember to fix this later.”

Across from the office a store needed more space. They put up an addition. The thing that struck me was the speed. A month or two from bare ground to a 20x20x10 meter (my really bad estimates here) structure standing there. Walls going up. Roof getting added.

Pre-manufactured parts. They just assembled what arrived.

Everyone talks about AI replacing programmers. I think it replaces something else entirely.

The experienced developer now has prefab components. The AI tools are the pre-manufactured pieces. You can assemble something real while the meeting to discuss whether to build it is still being scheduled.

The bottleneck shifts. It’s not “can we build this” anymore. It’s not even “how long will it take to build.”

It’s whether the organization can approve and validate as fast as you can build.

You could have a working prototype before the first planning meeting ends. The code can be written faster than the documentation explaining why we need it.

But here’s the question: do we trust a structure built in a day? How long does code need to sit before we believe it won’t collapse under pressure?

The building across the street will stand for decades. It better. But it was assembled in weeks because someone else already solved the hard engineering problems.

Same pieces we’re using now. Just faster assembly.

I write because I might be a few steps ahead of someone who wants to learn something new. Someone who needs a path forward.

We all have a unique mix of skills, behaviors and experiences. This combination becomes your unfair advantage when you share it.

Share your experiences.

“I might be wrong” is a cornerstone of how I manage. It keeps me flexible and open to reconsidering when someone explains I’m off base.

I’ve been taking improv classes for a couple of months now.

The thing I love most about improvisation is the feeling of a team working together toward a goal.

When we have aligned goals and clear structure, we trust each other and we want each other to succeed.

Then it is a marvel.

The problem isn’t with AI’s capabilities.

Companies are trying to automate chaos and expecting AI to magically create order from disorder.

I’ve been thinking about this lately. Not whether confirmation bias exists (it always has) but whether we’ve built an entire infrastructure around it.

The algorithms show us what we already believe (the filter bubble). ChatGPT is quick to tell us we’re right about things. And we’ve developed a whole subculture of just… cutting people off when they disagree. Unfriend, unfollow, block.

It’s not that any of these things are necessarily wrong on their own. But together they create something like a confirmation bias feedback loop. You think something, the algorithm reinforces it, the AI validates it, and anyone who might challenge it gets removed.

Maybe every age has its dominant cognitive trap. Ours just happens to come with decent UX.

Claude Code Web gave everyone $1000 credit to experiment with. I decided to build a restaurant catalogue chatbot for Umeå with full menu data.

The stack is Cloudflare: D1 for the database, Vectorize for semantic search, R2 for storage. Gemini parses uploaded menus. Perplexity fills in restaurant information. Sounds complicated but it’s fairly straightforward.

The workflow is what makes this interesting. Claude Code Web connects to a GitHub repo. I ask for a feature. It reads the code, makes edits, creates a PR. Cloudflare automatically deploys a feature branch with its own URL.

I test it on that URL. Ask for fixes if needed. Approve. It merges to main. Production deploys.

All of this from my phone.

I’ve made around 90 PRs. Spent about $100. That’s roughly $1.11 per shipped feature.

The constraint is being clear upfront. If I’m vague, Claude goes in the wrong direction and I waste iterations. When I’m precise, it usually nails the implementation.

The only real limitation is D1 migrations. Can’t run those from mobile. Though I could probably solve that with a GitHub Action.

I also bought a domain for 9 kronor.

It’s been a fun weekend experiment.

For the longest time there was a disagreement. It was about tabs vs spaces. Developers argued in threads and pull requests. No conclusion to what was better.

I jokingly always said ”one tab and one space” and very few laughed. That is how serious the ”war” was.

Then code completion, prettier and lint came along and the discussion ended.

I wonder what discussions we have today that will feel ancient in a couple of years time.

Micro-services? AI assisted coding? Type in JavaScript? The cloud?