Exclusive AI & LLM coaching for senior IT professionals from a Google Developer Expert (AI)
Exclusive AI & LLM coaching for senior IT professionals from a Google Developer Expert (AI)
Reading Time: 2 minutesYes, you read that right. In their rush to connect AI models to live data, developers have inadvertently left the door wide open. Researchers from Knostic scanned the web and found: One server even managed cost estimates…
Reading Time: 2 minutesThe setup: Models included Anthropic’s Claude Opus 4, Claude Sonnet 4, Claude Sonnet 3.7, Claude Sonnet 3.6, Claude Sonnet 3.5, Claude Haiku 3.5, and Claude Opus 3, Alibaba Qwen3-235B; DeepSeek-R1; Grok 3 Beta; Meta Llama 4 Maverick;…
Reading Time: 2 minutesBy now, at an individual level, we all have experienced AI going wrong – chatbot going off-script, – voice assistant misunderstanding us – image generation tool writing “Welcmoe” instead of Welcome on the image While these are…
Reading Time: < 1 minuteEveryone’s building LLM apps.But is anyone making them secure? Namaste, I am Nikhilesh. I teach AI and LLMs to senior IT professionals. And while most conversations revolve around building cool AI features like RAG, no one…
Reading Time: < 1 minuteWe often use these 2 terms interchangeably, but they are not the same. Let us understand the difference in simple language: Open-weight LLMs vs Open-source LLMs Open-Weight LLMs What it means: The model weights are released…
Reading Time: < 1 minuteBehind every intelligent system lies a team of professionals, each contributing a unique set of skills. A recent visual I came across illustrates this beautifully, showing how Software Engineers, Data Engineers, and ML Engineers/Data Scientists intersect…
Reading Time: 2 minutesWhile many are talking about better AI models, Amazon is building something even bigger, an entire AI ultra-cluster. Under Project Rainier, Amazon is constructing a constellation of massive data centres, starting with 7 in Indiana (and potentially…
Reading Time: 4 minutesThe challenge with AI agents is that they do not have a persistent memory. We have to manage their memory explicitly. For example – you are chatting with ChatGPT and later you close that session. When you…
Reading Time: < 1 minuteA real product solves a specific problem in a repeatable, trustworthy, and economically viable way. And that means understanding two very different costs: 1. Cost to build –> fast, cheap, often exciting. 2. Cost to own…
Reading Time: < 1 minuteThis sentence has a touch of sarcasm, but behind the sarcasm lies a real concern. As leaders, we must ask ourselves: Why does training often feel like “just another task” to our teams? Let’s be real,…