I have modified and followed the ICM strategy to imporve my folder structure with proper Context.md and other markdown file.. while this setup works well for Claude Code.. but i am facing issues when usung it with Github Copilot or Antigravity.. like they dont follow the instructions alot of times.. do not follow the files indexed.. etc.. i have added proper Agents.md/gemini.md/copilot-instructions.md but still the same problem Anyone else facing this problem? Please do tell me if there's a way which worked for you! Thanks

I am truly amazed by your content. Will it be possible for to create a video about obsidian and claude - obsidian as a second brain ( increase memory -> efficiency) . I am asking the community: who is interested to learn about it ? I can learn by myself but I am sure you will provide tips that will take me weeks to learn.

I'm about to start recording videos about my software development workflow. I keep telling people about it but i realized after a meeting today about setting up a local vibe coding competition that i should just pump out a program or two on a live stream and then figure out how to edit it down into actual educational videos(I am NOT a teacher). The question i have is would anyone be interested in knowing about when I'm going to be on so they can sit in on the process? This is not going to be an ongoing thing. Just making a few videos to show how I do things.

Hey I'm working in Antigravity and using Claude Code and hitting my limits daily. How do you handle hitting the limit? Do you have a workaround to deal with it? Certain tasks handled by other LLM? Complete switch after the limit is hit? What LLM do you switch to? I'm a bit nervous to use another LLM... afraid of the quality of the work it will do. A lot of questions in one post. 🤯 Please share your thoughts.

Sam Altman said something at the BlackRock Infrastructure Summit this week that crystallized a lot of my thinking. "We see a future where intelligence is a utility like electricity or water and people buy it from us on a meter." I've been saying a version of this for nearly a year. My one-liner in conversations: "We don't buy tools from the electricity company." We buy refrigerators from Samsung. TVs from LG. Light bulbs from Philips. Electricity just powers them. AI tokens are heading the same direction. The model providers (OpenAI, Anthropic, Google) will sell the raw intelligence. Everyone else builds specific tools that consume those tokens for specific jobs. Voice generation tools. Code review tools. Customer support automation. Research tools. Analytics platforms. Each one tailored to a workflow, a user, a problem. The model providers become the power grid. Everyone else builds the appliances. I'm not theorizing. I'm living this right now. I'm building 5+ AI-native products and services as a solo founder. One person. No team, no employees. A decade ago I tried something similar and failed badly. The infrastructure didn't exist. You needed teams of engineers and real capital to build anything meaningful. Today the infrastructure is here. One person can ship real products in weeks that would have taken months with a full team. People keep asking me "is AI a bubble?" I push back every time. I'm in it every day, building in the trenches. This doesn't feel like a bubble. It feels like a utility going live. For the automation builders here: how are you thinking about this shift? Are you building tools on top of AI APIs? And does the "utility" framing change how you think about your product's long-term defensibility?