Rx Note

Introduction Starting October 9, 2026, Google is limiting free personal Gemini accounts to the lightweight Flash-Lite model, eliminating free access to standard Flash and Pro models. Additionally, Google AI Plus subscribers are losing access to the Gemini Pro model, leaving Pro access reserved exclusively for higher-tier AI Pro and AI Ultra plans. Following the unveiling of the Gemini 4 Argon model, Google is reallocating its heavy compute power toward paying enterprise clients rather than subsidizing casual free users. Finding the Balance Between AI Token Costs and Human Effort Over the past few years, artificial intelligence (AI) has exploded in popularity. Almost every device and appliance now integrates AI features, including fridges and air conditioners. Many companies have pushed employees to leverage AI tokens for maximum productivity. Yet, despite all the hype, human input in daily tasks cannot be completely replaced. Along the way, organizations are discovering a critical rea...

Introduction "Time and tide wait for no man". We hear this constantly, whether from the CEO of Nvidia or from artificial intelligence companies pushing the narrative that AI is the new norm - one we must either embrace or be left behind by. Everywhere we turn, people are offering advice on how to optimize AI in our daily work. However, while I feel a sense of excitement about these advancements, I also harbour some serious reservations. The Illusion of the Infographic The most immediate impact I see in daily life is the lightning-fast generation of AI videos and infographics. Yet, far from being excited by these excellent graphics, I find myself a bit old-fashioned; I am not a person who loves visuals for the sake of it. In fact, it often takes more time to digest an infographic because we have to decipher the sequence and figure out the core message. More critically, infographics risk omitting crucial details that we might easily dismiss. We need to look beyond mere fascina...

Introduction On 20 March 2026, Google issued a notification regarding the sunset of Firebase Studio . Users are requested to migrate their projects during a one-year transition period. The decommissioning schedule is as follows: 19 March 2026: Sunset announcement; migration tools begin rolling out to Firebase Studio. 22 June 2026: New workspace creation is disabled. Users can still access and migrate existing workspaces. 22 March 2027: Official shutdown. All remaining data will be permanently deleted and cannot be recovered. To ensure continuity, users are encouraged to move their workflows to Google AI Studio (for web-based prototyping) or Google Antigravity (the agent-first desktop IDE). The Migration Path The official documentation suggests two primary migration paths based on your specific workflow: Migrating to Google Antigravity Recommended for a code-first, agentic development experience. Antigravity offers deeper control over your local codebase (e.g., managing npm packages)...

Introduction Artificial intelligence has been both feared and embraced as an essential component of technology. While some have worried that AI could eventually lead to the extinction of humanity, others have been fascinated by the possibilities it presents. AI Chatbots In 2023, there have been exciting developments in the field of AI, including the launch of conversational AI models such as ChatGPT by OpenAI, Microsoft Copilot and Gemini . These tools can generate plausible-sounding yet precise answers to a wide range of questions. In fact, ChatGPT may pass law school , medical school , or MBA exam. However, the rise of AI also raises concerns about job displacement and the potential for cheating in education. While ChatGPT offers impressive capabilities, it will not replace Google Search , because Life is complicated and conflicting in nature, saturated with grey areas. Humans like to hear a second opinion. Since ChatGPT was trained on a diverse range of text data (with no accur...

Introduction Before I began building Progressive Web Apps (PWAs) with the help of artificial intelligence , I believed I had a clear vision of what an ideal solution should look like. If I were fluent in programming, I could have implemented clean, bug-free solutions that precisely addressed user needs. In my view, a well-designed app should simplify workflows, rather than introduce friction or impose extra steps that do not align with real-world usage. However, in practice, developers may not fully understand the actual workflows, while users may not articulate their needs clearly or may passively accept whatever is given. In hindsight, I realised that my idealism about building a “perfect” app stemmed from a limited understanding of the technical foundations required to support such ambitions. What Users Take for Granted As users, we have grown accustomed to feature-rich, polished applications that just work. For example, a professional PDF editor is expected to support text highli...