What's harder than finding an answer is finding the right question that needs to be asked, and what's even hard is realizing there's a need for a question.

Kaptana Kapatna ki jana

Do it alone; Do it scared; Do it anyway.

You're under no obligation to remain the same person you were a year ago, a month ago, or even a day ago. You are here to create yourself, continuously.

Your assumptions are your windows on the world. Scrub them off every once in a while, or the light won't come in. -- Isaac Asimov

The most powerful tool of your mind is not its capacity to know, but its ability to question.

Knowledge grows when you ask stupid questions. Stupidity grows when you don't ask anything.

The first principle is that you must not fool yourself — and you are the easiest person to fool.

If intelligence is the ability to deal with what you weren't prepared for, then the modern AI strategy is to prepare for everything, so you never need intelligence. This is of course a terrible strategy, because it is impossible to prepare for everything. The problem isn't just scale, the problem is the fact that the real world isn't sampled from a static distribution -- it is ever changing and ever novel.

The difference between a good student and a great one is that a good student is concerned more about the outcome while a great one is fascinated by the process of learning.

Primary Factor for Human Intelligence lies in identifying that there is a need to learn something.

The Kalman Filter was once a core topic in EECS curricula. Given it's relevance to ML, RL, Ctrl/Robotics, I'm surprised that most researchers don't know much about it, and many papers just rediscover it. KF seems messy & complicated, but the intuition behind it is invaluable 1/4