Hearing how Uber scaled to 1.500 AI agents made me realize just how quickly things can spiral when those agents start acting faster than humans can keep up.
This March at CTO Craft Conference in London, I sat down over dinner with 13 senior leaders and CTOs and had the kind of conversation you rarely get at conferences. There were no slides or presentations, just talk about how AI implementation works in different companies.
Vibe coding stopped feeling like an experiment and became something... else. Many people using it couldn’t really explain what they’ve built, just that it works. Until it doesn’t.
I spoke with four veteran software engineers to explore how they’re approaching long-term career resilience and adapting their skills to stay effective in the field.
I was at the MCP Dev Summit North America and heard from its co-creator, David Soria Parra, that the question is no longer how to use MCP, but what breaks when you try to scale it.
92% of developers use AI coding tools, but productivity has barely moved - stuck at 10%. Here’s why using AI doesn’t automatically mean getting more done.
As AI tools become part of developers’ everyday workflows, a lot of engineering leaders assume that getting started is just a matter of buying the right software.
When was the last time a dev conference taught you something you couldn’t learn online? Probably never. But that’s the wrong benchmark - conferences were never just about information.
What if I told you that understanding AI is a bit like juggling knowledge about Marvel, DC, Matrix, Harry Potter, Lord of the Rings, and Pokémon franchises? Crazy, right? But hear me out.