Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I spent some time last week vibe-coding "The Beginner's RL Playground" a simple web tool for exploring many basic concepts in reinforcement learning. Users can adjust all sorts of parameters of the algorithm and environment and see the effects of those changes in realtime.

awjuliani's profile picture

Arthur Juliani

8,313 subscribers

45,743 görüntüleme • 1 yıl önce •via X (Twitter)

Sağlık & İyilikEğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

I think it's interesting that we're starting to see different types of specialists emerge in the field of Generative AI technology. We are seeing a new generation of world-class storytellers. Some are immaculate at vibe coding workflows and building infrastructures. Some are incredible at AI visual effects and AI cinematography. And some are just maestros at composition and world-building. And of course, many of us dip into all facets. We are witnessing the emergence of new creative and technical roles that didn't exist yesterday, and that's very exciting. And now we are starting to see the benefits of AI as an additive to existing workflows. I hope to work with many of you for the upcoming productions we have in the works at Promise.
0:16

I think it's interesting that we're starting to see different types of specialists emerge in the field of Generative AI technology. We are seeing a new generation of world-class storytellers. Some are immaculate at vibe coding workflows and building infrastructures. Some are incredible at AI visual effects and AI cinematography. And some are just maestros at composition and world-building. And of course, many of us dip into all facets. We are witnessing the emergence of new creative and technical roles that didn't exist yesterday, and that's very exciting. And now we are starting to see the benefits of AI as an additive to existing workflows. I hope to work with many of you for the upcoming productions we have in the works at Promise.

Dave Clark

13,168 görüntüleme • 1 yıl önce

spent the better part of the week building little animated diagrams like this one i hope those will help illustrating some of the concepts behind the example scenes i'm preparing for the upcoming blog post
0:12

spent the better part of the week building little animated diagrams like this one i hope those will help illustrating some of the concepts behind the example scenes i'm preparing for the upcoming blog post

Maxime

49,591 görüntüleme • 10 ay önce

All men should do 100 of these movements everyday and see the changes in one week.
0:19

All men should do 100 of these movements everyday and see the changes in one week.

Prince Fynn

80,593 görüntüleme • 1 gün önce

Just spent the last 4 days on a sailboat exploring the Flores and Komodo islands in Indonesia and I have to say, undoubtedly one of the most beautiful places in the world.
0:35

Just spent the last 4 days on a sailboat exploring the Flores and Komodo islands in Indonesia and I have to say, undoubtedly one of the most beautiful places in the world.

Arnaud Bertrand

146,023 görüntüleme • 1 yıl önce

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.
0:12

These are not CGI. Reinforcement learning is so back. When operating on strings, it gives us o3. When operating on physical motors, it gives us a perfect humanoid backflip and a robot creature that out-maneuvers almost every animal on earth. RL is one of the only learning algorithms that can master both the world of bits and the world of atoms. Give me a reward function, and I shall move the world. 2025, Year of RL.

Jim Fan

356,800 görüntüleme • 1 yıl önce

Users of most AI coding products are still stuck in the vibe-coding loop: Prompt → Test → Debug → Adjust → Fix Errors → Repeat Bubble Code users take a different path. State the product goal. If the result needs improvement, submit a Bubble Up. Then Bubble Engine takes over: testing, evaluating, and optimizing the SOP behind the scenes — turning one hard task into a reusable execution path. Not endless vibe coding. Better SOPs, upgraded by the Bubble Engine.
0:14

Users of most AI coding products are still stuck in the vibe-coding loop: Prompt → Test → Debug → Adjust → Fix Errors → Repeat Bubble Code users take a different path. State the product goal. If the result needs improvement, submit a Bubble Up. Then Bubble Engine takes over: testing, evaluating, and optimizing the SOP behind the scenes — turning one hard task into a reusable execution path. Not endless vibe coding. Better SOPs, upgraded by the Bubble Engine.

DAPPOS

25,865 görüntüleme • 1 ay önce

In our wizard game, you can use the basic spell for all sorts of important wizard hijinks, including pushing students over (gently, of course), moving items around, opening containers, and much more!
0:12

In our wizard game, you can use the basic spell for all sorts of important wizard hijinks, including pushing students over (gently, of course), moving items around, opening containers, and much more!

John Szymanski (Ducky)

125,401 görüntüleme • 2 yıl önce

Spent some time last week building up a new detail screen in Believe. This is just the start of a journey introducing more community and creator focused changes we have coming. I wanted to make this fun, playful but equally useful. I am excited to deliver more polish and introduce community focused features to the rest of the app. Time to take things to the next level🫡
0:13

Spent some time last week building up a new detail screen in Believe. This is just the start of a journey introducing more community and creator focused changes we have coming. I wanted to make this fun, playful but equally useful. I am excited to deliver more polish and introduce community focused features to the rest of the app. Time to take things to the next level🫡

Joseph Smith

51,869 görüntüleme • 11 ay önce

10 months in the gym and I can finally see the start of some actual muscle underneath those tits. I am beyond excited!
0:12

Sensitive content

10 months in the gym and I can finally see the start of some actual muscle underneath those tits. I am beyond excited!

DQPeaks

39,931 görüntüleme • 2 ay önce

How'd you like a business where you can spend $1,600 once and make $1,600 in profit every month? Last week I spent the day at one of these businesses and learned all I could from the owner. Here's what's good:
0:15

How'd you like a business where you can spend $1,600 once and make $1,600 in profit every month? Last week I spent the day at one of these businesses and learned all I could from the owner. Here's what's good:

Chris Koerner

123,418 görüntüleme • 1 yıl önce

I lived in PR for 6 months. I have spent time in the mountains of Peru, the cloud forests of Costa Rica and the Amazon of Ecuador. I even lived in a treehouse village in The DR for a week. I have never seen a wetter summer than this one in DC! We aren’t supposed to get monsoons!
0:17

I lived in PR for 6 months. I have spent time in the mountains of Peru, the cloud forests of Costa Rica and the Amazon of Ecuador. I even lived in a treehouse village in The DR for a week. I have never seen a wetter summer than this one in DC! We aren’t supposed to get monsoons!

AntifaPuddin’Pop

95,528 görüntüleme • 1 yıl önce

A simple rope and pulley system can help you achieve all sorts of things in the garage. Lifting, moving, suspending… or even silly things like this!
0:15

A simple rope and pulley system can help you achieve all sorts of things in the garage. Lifting, moving, suspending… or even silly things like this!

Theogcfu

171,792 görüntüleme • 2 ay önce

Posted a full preview of this in my discord, here's a snippet! This is the culmination of all the stuff I've been learning the last few months. There's a Daz3d model in there being driven by motion capture data, with a physics driven hair rig and some basic jiggle on the boobs.
0:14

Posted a full preview of this in my discord, here's a snippet! This is the culmination of all the stuff I've been learning the last few months. There's a Daz3d model in there being driven by motion capture data, with a physics driven hair rig and some basic jiggle on the boobs.

Size King

11,648 görüntüleme • 1 yıl önce

Reinforcement Learning (RL) has long been the dominant method for fine-tuning, powering many state-of-the-art LLMs. Methods like PPO and GRPO explore in action space. But can we instead explore directly in parameter space? YES we can. We propose a scalable framework for full-parameter fine-tuning using Evolution Strategies (ES). By skipping gradients and optimizing directly in parameter space, ES achieves more accurate, efficient, and stable fine-tuning. Paper: Code:
0:16

Reinforcement Learning (RL) has long been the dominant method for fine-tuning, powering many state-of-the-art LLMs. Methods like PPO and GRPO explore in action space. But can we instead explore directly in parameter space? YES we can. We propose a scalable framework for full-parameter fine-tuning using Evolution Strategies (ES). By skipping gradients and optimizing directly in parameter space, ES achieves more accurate, efficient, and stable fine-tuning. Paper: Code:

Yulu Gan

415,325 görüntüleme • 10 ay önce

𝕏’s algorithm is changing in real time And many new features & updates are rolling out soon The average time spent on 𝕏 is already up over 20%, and follows are rising too And this is just the beginning 𝕏 is becoming a daily habit for millions of people, it's the last place where free speech still exists
0:15

𝕏’s algorithm is changing in real time And many new features & updates are rolling out soon The average time spent on 𝕏 is already up over 20%, and follows are rising too And this is just the beginning 𝕏 is becoming a daily habit for millions of people, it's the last place where free speech still exists

X Freeze

14,587 görüntüleme • 7 ay önce

Over the weekend, I started learning SwiftUI. After spending some time to learn the basics, with the help of ChatGPT and of GLSL coding knowledge, I created my very first app. More info and source code shared below 🧶
0:12

Over the weekend, I started learning SwiftUI. After spending some time to learn the basics, with the help of ChatGPT and of GLSL coding knowledge, I created my very first app. More info and source code shared below 🧶

vijay verma

167,156 görüntüleme • 3 yıl önce

Now you can see and control your Instagram algorithm from your Explore page to see more of the topics you’re into 🔎 (Available to English-speaking users in most countries.)
0:19

Now you can see and control your Instagram algorithm from your Explore page to see more of the topics you’re into 🔎 (Available to English-speaking users in most countries.)

Instagram

122,900 görüntüleme • 3 ay önce

Look for 25 of the most-searched people, places and things of all time, hidden in our Most Searched Playground. Play now → #YearInSearch
0:16

Look for 25 of the most-searched people, places and things of all time, hidden in our Most Searched Playground. Play now → #YearInSearch

Google

121,631 görüntüleme • 2 yıl önce

The man has spent the last year and a half fighting one of the largest military forces in the world and the best Pierre Poilievre can do is give a half-hearted round of applause for the President of Ukraine. #cdnpoli
0:14

The man has spent the last year and a half fighting one of the largest military forces in the world and the best Pierre Poilievre can do is give a half-hearted round of applause for the President of Ukraine. #cdnpoli

Mark Gerretsen 🇨🇦 🇺🇦

2,683,557 görüntüleme • 2 yıl önce