Artificial Intelligence

I set out to see how easily an AI agent could be manipulated by harmless-looking spreadsheets, so I kept escalating the prompt injection until it either caught on or took the bait.

We spoke with 3 engineers to ask the blunt question: is AI making junior developers better or just faster at shipping code?

We make many mistakes with MCPs, but one of the biggest is treating them like a 1:1 REST API mapping - when in reality, an MCP tool should be a capability, not just another endpoint.

Everyone is busy asking how big the model is, but the real question is what you fed it first - because if your PDFs are mangled and your OCR is sloppy, even the smartest LLM starts from the wrong answer.

Jordan Topoleski (COO, Cursor) and Pallavi Mahajan (CTO, Nokia) made the case that the next real breakthrough in AI development is agent orchestration.

AI agents are already being trusted with real work, but handing them raw credentials is a dangerous shortcut. That's why the next security challenge is controlling what an agent can do once it gets access.

Mike Chambers, Developer Advocate at AWS, says the real test of AI is not whether a demo looks smart, but whether the system around it can survive real-world use.

Engineering teams are starting to resemble legacy Java apps hitting thread exhaustion. I believe change is unavoidable, and we need a better way to organize the work.

The fastest way to create technical debt in AI is still the oldest one: choosing a database because it feels comfortable.

The AI boom is no longer just a race to build faster machines. The real challenge now is making all the moving parts work together at scale.

At the AI Engineer conference in San Francisco, I heard Instagram co-founder Mike Krieger say developers no longer need to review every line of code by hand. The real job now is judging AI’s decisions and whether the product solves the right problem.

A new kind of builder is emerging inside organizations - one that works fast, ships often, and rarely follows the instincts of a software engineer. That raises a simple question: what happens to security?

AI can write the code. The harder question is whether anyone still understands what it was supposed to do six months later.