Topic: AI.
Posts on AI in real product and engineering work: building AI-powered tools, using large language models for SEO and data platforms, and honest takes on where AI actually helps versus where it's overhyped.
Every test passed. The customer got refunded twice.
AI built your refund feature in seconds. It even wrote the tests. Everything passed. Then a customer got their money back twice. Turns out, nobody mentioned that part. Before you spend another afternoon perfecting your prompts, try writing down the rules your software actually needs to follow.
My 3 Cents on the Future of Software Engineering Jobs.
Will AI make software engineering jobs disappear? My bet is quite the opposite. Engineers have always filled the gaps in requirements and design, making hundreds of decisions along the way. With agents taking on more coding, we have time to take on more responsibility. Folks in other roles: we’re coming for you. Mostly joking.
Everyone is an AI Expert. Some Even Use It!
Yesterday, I attended After-hours: AI Talent, organised by EDB Singapore. Great opportunity to meet interesting people, exchange ideas and see how AI is reshaping business. One observation? AI is no longer just a technology topic. It's becoming a business imperative. And apparently, everyone is an AI expert these days. Some even use it!
Vietnam’s Tech Job Market Is Back. Unfortunately, So Is Everyone Else.
Vietnam’s tech job market is healthier again, with fresh investment and growing demand in AI, data, cloud and semiconductors. Getting hired, however, is not getting easier. Local talent is stronger, employers are pickier and half of Southeast Asia now wants to become the next tech hub.
SDD Might Be the Answer - Once We Agree What It Means.
Spec-driven development is gaining attention as developers look for a more reliable way to build software with AI. The idea makes sense: describe clearly what should be built before asking AI to build it. I’m on board - but until we agree on what a good specification actually looks like, SDD risks becoming another label everyone uses differently.