Scripture like Bhagavad Gita was not written so you could quote it- memorize the Sanskrit shlokas. It was written so that when your own battlefield arrives, when you’re standing in Kurukshetra of your life, and that will happen, you would already know how to stand and win your life’s battle. Same with the Ramayana, or YogSutras by Patanjali or Upanishads. These are not for intellectualization of texts but living manuals. Practicing these in your daily life matters more than quoting the Sanskrit shlokas to prove that you are well versed with them.
For those who are not diabetic or clinically obese, diet & exercise should be first option. GLP-1 alters metabolic function n has neurological signalling which in the long term may have side effects. There is not much long term data on chronic use of GLP-1s.
The advice to early founders is always cut costs and extend runway. My experience of working with 45 companies in our portfolio is- runway buys you time but it doesn't make you win. You win with revenues. At some point you have to make the thing people will actually pay for. Everything else is just delaying that conversation. 70% of startups who shutdown in general- ran out of cash. They died because they built something people wouldn't pay for. Runway doesn't save companies, revenue does. Everything else is just borrowed time.
The biggest barrier to building an app is now gone 🔥
You no longer need to learn coding.
Just describe your idea in plain English to Claude → It builds the full app → Push to GitHub → Deploy on Vercel.
And boom… you have a live app.
2026 mein coding sirf ek formality reh gayi hai.
If you’ve been waiting to build your idea “when you learn coding” — your excuse just expired.
Who’s building their first app this month? 👇
Follow @aishivamx for more AI tools & productivity hacks.
for anyone asking where to learn this stuff:
• RAG → https://t.co/4bzbUIwV5g
• Agentic RAG → https://t.co/IotOiGmV1Y
• AI Agents → https://t.co/nEeMnVJQbk
• Multi-Agent Systems → https://t.co/pavDPVJEFj
• LangGraph → https://t.co/3miEqqFzF0
• LangGraph (code) → https://t.co/v7kxHZXqba
• MCP → https://t.co/lKawRb4etX
• Memory Systems → https://t.co/LSaT2UaPAS
• Evals → https://t.co/vxChxa1kqQ
• Context Engineering → search "Context Engineering Survey" on arXiv
and please skip the "build an ai agent in 10 minutes" videos
build something, watch it fail, then figure out why.
I find it odd when people turn businessmen into role models, and this seems to have become more common in the last 5-odd years. It's the same with idolising movie stars and sports stars. None of it should happen, really. 😀
When people come to me for advice, my first reaction is: What makes you think I'm qualified?
Just because I've gotten lucky in business, does that make me qualified to advise you on your career, your life choices, or anything apart from how to get lucky? 😀
There are startup founders, especially people working in the social sector, whom I meet through @RainmatterOrg, and I think they are far smarter and more capable of giving advice than I am.
If you still pick a role model, pick someone for a trait worth admiring in real life, not because of what they project to the outside world.
Wow, this tweet went very viral!
I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, there is less of a point/need of sharing the specific code/app, you just share the idea, then the other person's agent customizes & builds it for your specific needs.
So here's the idea in a gist format: https://t.co/NlAfEJjtJV
You can give this to your agent and it can build you your own LLM wiki and guide you on how to use it etc. It's intentionally kept a little bit abstract/vague because there are so many directions to take this in. And ofc, people can adjust the idea or contribute their own in the Discussion which is cool.
Who wants to know how Gemma 4 works?
This visual guide breaks down the new architectures and how they process text, images, and (for the smaller models) audio.
👇
Georgia Tech built a free tool that animates every data structure and algorithm in real time
https://t.co/8d8o08lBta
this is what DSA study looks like when it actually makes sense