for each task, I create a manager subagent that has a clearly defined goal.
it works with worker subagents until the goal is achieved through a loop system for correctness.
I record all my research meeting transcripts using @meetgranola , but transcripts are useless if you don't do anything with them --
I built a research assistant to help plan tasks and execute in the same window using @claudeai SDK.
more coming soon
behind every successful product release, research publication, hackathon win... is hours of work behind the scenes that is not seen
many of us aren't obsessed enough to put in the work to reach the point of success
NVIDIA started with the wrong technology, learned the right one from three textbooks bought at Fry’s, and went on to invent most of the major breakthroughs in modern computing.
At Startup School 2026, YC's @garrytan sits down with @nvidia Founder and CEO @JensenHuang to talk about confronting reality, learning your way into new domains, and why resilience — getting through one day at a time — matters more than anything else.
01:07 — NVIDIA's wrong algorithm
03:14 — Buying textbooks to save the company
05:29 — The real big idea
07:06 — The Sega story
09:37 — The $300M IPO
10:33 — Seeing AlexNet differently
12:44 — Reinventing the full stack
13:30 — How to build a first-principles org
17:01 — Build the car to fit your driving style
19:12 — Frontier algorithms
20:50 — Systems thinking is the new coding
23:26 — Should you own your own AI?
25:43 — How NVIDIA sses agents internally
30:51 — AI and job creation
34:21 — The ChatGPT moment for robots
37:24 — Where physical AI shows up first
39:18 — Why Jensen just joined X
41:01 — What to learn that still matters
44:32 — The mindset you should have - "How hard can it be?"
the exciting part about building a startup isn’t announcing that you’re working at a startup
it’s the possibility of having a large, positive, effect on a great number of people