François Chollet @fchollet Deep learning @google. Creator of Keras, neural networks library. Author of 'Deep Learning with Python'. Opinions are my own. Apr. 06, 2019 1 min read


1) Make something. It sucks.
2) Realize it sucks.
3) Actually care about it.
4) Find ways to improve.
5) Try again; repeat forever.

A lot of people get stuck at either 2) or 3).

4) and 5) are practically automatic if you pass 3).

If you give up after realizing you suck -- you didn't care enough. Caring is persevering. Forever.

If you don't have sufficient taste or vision, or if you are never exposed to the best, you will fail 2). You'll never realize your output is terrible. So seek out environments that will humble you

If you are content with mediocrity, or you don't want to admit to mediocrity ("I'm just not made for this, let's never do it again"), you will fail 3). To learn, you need to care. You need intrinsic drive.

You can follow @fchollet.


Tip: mention @threader_app on a Twitter thread with the keyword “compile” to get a link to it.

Enjoy Threader? Sign up.

Threader is an independent project created by only two developers. The site gets 500,000+ visits a month and our iOS Twitter client was featured as an App of the Day by Apple. Running this space is expensive and time consuming. If you find Threader useful, please consider supporting us to make it a sustainable project.