Alex V

[Alex V @AVavvas]

@KaufmanRoni @openprocessing @processing These are amazing, well done! Mind sharing a tiny bit about the process?

[François Chollet @fchollet]

When dealing with a high-complexity, high-uncertainty problem, if you think you know what you're doing, you probably don't know what you're doing.

Be aware of your own biases & weaknesses, and hedge your potential mistakes

[Alex V @AVavvas]

@ElliottVenczel Antonio Carlos Jobim - Heatmiser

I remember he said it was one of his favorites growing up.

[François Chollet @fchollet]

Not committing your entire career to one specific tool enables you to be more objective about its strengths, its limitations, and its future potential.

[eno Rogue @ZenoRogue]

How should a person exploring exotic geometries be called? A geometronaut?

[Greg Brockman @gdb]

We gave our AIs the goal of winning at hide-and-seek. They discovered tool use: https://t.co/VD24kUlOnj

[Alex V @AVavvas]

@mbereshb @Grummz We formed a queue too!

[hardmaru @hardmaru]

A Style-Based Generator Architecture for Generative Adversarial Networks. @NvidiaAI does it again! https://t.co/W2Av34ta9O

[hardmaru @hardmaru]

If we remove all design constraints, the optimizer came up with a really tall bipedal walker robot that “solves” the task by simply falling over and landing near the exit.

[Reckful @Byron]

Socials:
https://t.co/SRKPAqd5yD
https://t.co/m6k8WidsU1
https://t.co/TDyw6P6Ztt

Lucky tweet #7777 is this announcement:
Game name: Everland
Discord: https://t.co/0MGvmCYmo6
Twitter: https://t.co/HvL7tJ5Qmr
Website: https://t.co/LlFnzf6Zzb

[VentureBeat @VentureBeat]

Google's DeepMind taught AI teamwork by playing Quake III Arena https://t.co/iZ3tvUHuGL by @kharijohnson

[Keaton Patti @KeatonPatti]

I forced a bot to watch over 1,000 hours of Bob Ross videos and then asked it to write a Bob Ross video of its own. Here is the first page.

[François Chollet @fchollet]

We haven't yet solved even 10% of the problems we could solve with existing AI/ML techniques. Even if new research were to deliver nothing from now on, there still wouldn't be another AI winter. AI/ML will keep on delivering for years to come.

[François Chollet @fchollet]

Also, I don't like the view that a lack of motivation in the context of education is a personal failing. That's like saying that not having fun while playing a video game is your fault, rather than the fault of the game designers. Motivation should be part of curriculum design.

[Ziqo @Ziqoftw]

Sometimes u just gotta go out and meet new people, its too easy to get stuck in patterns

[hardmaru @hardmaru]

“Instead of trying to solve every problem with a single language, in my case: C++, and become an entrenched ‘C++ expert’, it is much more enjoyable and productive to learn a few different languages and pick a language that naturally fits a problem.” https://t.co/yoHST4RVRa

[hardmaru @hardmaru]

Playing hard exploration games by watching YouTube (DeepMind). One-shot imitation allows an agent to exceed human-level performance on the infamously hard exploration game Montezuma's Revenge, even if the agent isn't presented with any environment rewards. https://t.co/kpsFtfJH2W

[hardmaru @hardmaru]

Rocket Lander OpenAI Gym environment inspired by SpaceX's Falcon 9 vertical landing, using Box2D physics engine. They experiment using PID, MPC control benchmarks, and also tried DQN, DDPG ... https://t.co/egb9iyCtPS

[Jebbery... @jebbery]

Machine learning job interview

[Alex V @AVavvas]

@gempir @ByronBernstein Most of the times it should be enjoyable though, is it not? For me learning new technologies is a way to relax in a sense.