I've been thinking for quite some time now on how to build a framework for AI adoption. Not the theoretical kind, but the kind where a business can look at its own operations
The surprising part: H100 access felt almost trivial This week I experimented with vast.ai, a marketplace where you can rent GPU hardware on demand for AI workloads. I walked in expecting friction. Provisioning
Stop Treating Architecture Strategy as a Tech Wishlist Most engineering teams build architecture strategies backwards. They start with technology preferences, debate microservices versus monoliths, argue about which database to use, and then try
China Doesn't Need Better AI Models to Win the Market I said I'd write this article, so here it is. I believe that in the race for AI, China already has a structural
The renter problem: why cloud LLMs feel inevitable (until they don't) If you work with AI in any serious capacity, you're probably sending requests to an API. Claude, GPT, Gemini. You paste in
The Per-User Product: How LLMs Are Forcing a New SaaS Architecture When Every User Can Get a Different Product I've been thinking about where software architecture is headed in the context of LLMs,
When code stops being the source of truth A paradigm shift is emerging in software engineering: Requirements, not Code, are becoming the Source of Truth. For decades, engineers have treated code as the
This week I kept circling back to the same idea: the tools are getting smarter, but the real advantage is still how fast you and your team can learn.One thread is where LLMs
Technical TL;DR (for busy engineers) Static weights are the bottleneck. Most LLMs can infer in-session, but they don't durably update from experience unless you retrain or fine-tune. Context windows, RAG, and "memory" features help,
TL;DR Time invested: ~4 weeks of focused preparation Resources used: Frank Kane's Udemy course, Stephane Maarek's AI Practitioner tests, Tutorials Dojo practice exams, AWS documentation, hands-on Bedrock projects Difficulty level: Hardest AWS exam