Mekus Mekus

As someone who owns both a car and a motorcycle, keeping track of preventive maintenance has always been more annoying than it should be. Oil changes, brake servicing, tire replacements, coolant flushes, and all the other maintenance schedules were scattered across reminders, notes, and my memory. Every time I wondered, " When did I last change the engine oil? " I found myself digging through old receipts or guessing. I wanted something simple. An app where I could manage both vehicles in one place without creating an account, relying on cloud storage, or needing an internet connection. So last Sunday, July 5, I turned this idea into reality with the help of AI, and it became MotoCar PMS .     Instead of opening VS Code immediately, I started with ChatGPT. Rather than asking it to generate code, I asked it to interview me about the app I wanted to build. We discussed who the app was for, what problems it should solve, what features belonged in an MVP, and what success would l...

Last month, I stumbled across an article about a new AI agent called Manus that was making waves in tech circles. Developed by Chinese startup Monica, Manus promised something different from the usual chatbots – true autonomy. Intrigued, I joined their waitlist without much expectation. Then yesterday, my inbox pinged with a surprise: I'd been granted early access to Manus, complete with 1,000 complimentary credits to explore the platform. As someone who's tested every AI tool from ChatGPT to Claude, I couldn't wait to see if Manus lived up to its ambitious claims. For context, Manus enters an increasingly crowded field of AI agents. OpenAI released Operator in January, Anthropic launched Computer Use last fall, and Google unveiled Project Mariner in December. Each promises to automate tasks across the web, but Manus claims to take autonomy further than its competitors. This post shares my unfiltered experience – what Manus is, how it works, where it shines, where it st...

A new approach to software development, known as " vibe coding ," has started to emerge that promises to make creating software easier. Through interaction with artificial intelligence (AI), people prompt AI systems using natural language to specify their desired code. People can be authors of software without needing a background in programming. While this new technique generates excitement, it also raises many important questions regarding code quality, security, and the future of software engineers. The term, "vibe coding," was coined in early 2025 by Andrej Karpathy , a co-founder of OpenAI. Vibe coding is when users describe the desired functionality of software to large language models (LLMs) trained for coding in natural language. This is fundamentally different from coding in a conventional sense or writing code manually, and it may open software development to a much wider audience as Karpathy jokes: "the hottest new programming language is English....

The landscape of artificial intelligence continues to evolve at a breathtaking pace, and at the forefront of this innovation is Google's Gemini family of models. Recently, Google has expanded the capabilities of Gemini 2.0 Flash , introducing an exciting experimental feature: native image generation . This development marks a significant step towards more integrated and contextually aware AI applications, directly embedding visual creation within a powerful multimodal model. In this post, we'll delve into the intricacies of this new capability, exploring its potential, technical underpinnings, and the journey ahead. Introduction to Gemini 2.0 Flash Gemini 2.0 Flash is a part of Google's cutting-edge Gemini family of large language models, designed for speed and efficiency while retaining robust multimodal understanding. It distinguishes itself by combining multimodal input processing, enhanced reasoning, and natural language understanding . Traditionally, generating ima...

I recently had the privilege of stepping into the vibrant halls of La Consolacion University Philippines - Main Campus in Malolos, Bulacan, as a resource speaker for Grade 11 and 12 students specializing in Technical-Vocational-Livelihood (TVL) Computer Programming and Computer System Servicing. The event, titled  Equipping Future Tech Professionals: A Work Immersion Seminar-Workshop on AI, Cybersecurity, and Robotics , was held at the St. Augustine Building - AVR. While the broader seminar covered various topics, I delivered a focused talk on Artificial Intelligence specifically Generative AI (GenAI), aiming to introduce these young minds to one of the most transformative technologies of our time. Reflecting on the experience, I am filled with gratitude, inspiration, and a renewed sense of purpose. Why Generative AI? Generative AI is not just a buzzword—it’s a paradigm shift. As industries worldwide embrace AI-driven solutions, it’s crucial for the next generation of tech pro...

Google has taken another giant leap forward in the world of Artificial Intelligence (AI) with the introduction of Gemini 2.0 . This isn’t just another AI model; it’s a family of models designed to change how we interact with technology, ushering in what Google calls “the agentic era.” The first member of this family making its debut is Gemini 2.0 Flash , an experimental model created with a focus on speed and powerful performance. What sets Gemini 2.0 apart is its ability to go beyond simple conversations. It’s designed to take action, performing tasks independently and fundamentally changing user experiences across Google's range of products. Gemini 2.0 Flash: A Multimodal Powerhouse Gemini 2.0 Flash isn't just an upgrade; it's a multimodal powerhouse built for speed and efficiency. Building on the popularity of Gemini 1.5 Flash, this new model boasts enhanced performance while retaining rapid response times. In fact, Gemini 2.0 Flash surpasses the performance capabil...