1d ago · 2 min read · Context I used to think LLMs were like databases—you ask a question, you get the stored answer. But after playing with Temperature and System Prompts, I realized they are more like improv actors. They
Join discussion
3d ago · 5 min read · You spend an hour crafting the perfect persona. A meticulous project manager. Formal tone. No code unless asked. Clear status updates. You load it into Claude Opus. It works beautifully. The agent stays in character, follows every instruction, mainta...
Join discussionMar 27 · 3 min read · I got fed up. Every time I was deep into a conversation with Claude, the screen would suddenly say “Session limit reached” and kick me out. Even though I had credits. Even though I was paying. It felt
Join discussionMar 25 · 3 min read · Journey Context After 6.5 years of building react-native apps. Most of my work has been focused on building production apps, integrating APIs, optimizing performance, and shipping features. But instea
Join discussion
Mar 18 · 8 min read · I built the system behind this article while working on YouxAI, and the examples come from code I authored and refactored. AI was used to help draft and edit the article structure, but the technical c
Join discussionMar 13 · 5 min read · For years, local LLMs were functional but blind. We interacted with them through text, fed them structured data, and received text in return. If we wanted an AI to analyze an image, we had to "bolt on
Join discussion
Mar 6 · 5 min read · You spend an hour crafting the perfect persona. A meticulous project manager. Formal tone. No code unless asked. Clear status updates. You load it into Claude Opus. It works beautifully. The agent stays in character, follows every instruction, mainta...
Join discussion
