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.
> subscribe shift-mag --latest
Sarcastic headline, but funny enough for engineers to sign up
Get curated content twice a month
Written by people, not robots - at least not yet. May or may not contain traces of sarcasm, but never spam. We value your privacy and if you subscribe, we will use your e-mail address just to send you our marketing newsletter. Check all the details in ShiftMag’s Privacy Notice
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.
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.
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.
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.
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.