Loading video...

Video Failed to Load

Go Home

5.6 Sol on Codex one-shotted a second-screen experience for Project Diablo 2. It did a fork of GameNative and added a new native Kotlin extension. Compiled it, installed it, ran and tested it. Never ceases to amaze me.

Dimillian's profile picture

Thomas Ricouard

61,363 subscribers

94,026 views • 21 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Here is a recreation of the World Cup final on a desk! It fetches game data from an API and other sources, and stores it in Supabase to project it onto a desk in an immersive experience! Amazing to see what Codex and Supabase can create for us!
0:12

Here is a recreation of the World Cup final on a desk! It fetches game data from an API and other sources, and stores it in Supabase to project it onto a desk in an immersive experience! Amazing to see what Codex and Supabase can create for us!

Tyler Shukert

20,156 views • 2 months ago

My best grokbot use case yet. I told it to build a chrome extension that shames me when on procrastinate on social media. Now, when I go to X or Linkedin, it bricks my screen & I have to record a video of me saying "I'm being a bad, bad boy" to unlock the app. It one-shotted this sucker.
0:15

My best grokbot use case yet. I told it to build a chrome extension that shames me when on procrastinate on social media. Now, when I go to X or Linkedin, it bricks my screen & I have to record a video of me saying "I'm being a bad, bad boy" to unlock the app. It one-shotted this sucker.

Alex Lieberman

41,339 views • 1 month ago

Codex users: *THIS* is the best way to take advantage of the GPT-5.6 Luna Max capability and 80% price reduction. Treat Luna Max as a 'subagent' by instructing the Sol orchestrator to spin up and monitor a separate thread. Added to 'sol-advisor'. Try it out below 👇
0:19

Codex users: *THIS* is the best way to take advantage of the GPT-5.6 Luna Max capability and 80% price reduction. Treat Luna Max as a 'subagent' by instructing the Sol orchestrator to spin up and monitor a separate thread. Added to 'sol-advisor'. Try it out below 👇

Dan McAteer

56,039 views • 1 month ago

Ran Atria Dawn Preview (Atria ASI) on a real task tonight, not a demo script. Gave it one line through Codex: build a CLI that pulls my last 10 X posts' engagement stats into a CSV. Back in 2 minutes. It wrote the script, mock-tested the output, then wrote and ran its own unit tests. All passed.
0:17

Ran Atria Dawn Preview (Atria ASI) on a real task tonight, not a demo script. Gave it one line through Codex: build a CLI that pulls my last 10 X posts' engagement stats into a CSV. Back in 2 minutes. It wrote the script, mock-tested the output, then wrote and ran its own unit tests. All passed.

Shraddha Bharuka

26,052 views • 7 days ago

GPT-5.6 Sol is seriously impressive. I used it to create the prompt for this Peking Opera video. It did a great job capturing the cultural elements and visual language. Prompt below ⤵️
0:15

GPT-5.6 Sol is seriously impressive. I used it to create the prompt for this Peking Opera video. It did a great job capturing the cultural elements and visual language. Prompt below ⤵️

Kiki

31,048 views • 2 months ago

Evergrow, barely a weekend project. Astra now got it running on the AYN Thor wrapped into an APK with a second screen experience. This is insane.
0:17

Evergrow, barely a weekend project. Astra now got it running on the AYN Thor wrapped into an APK with a second screen experience. This is insane.

Thomas Ricouard

11,622 views • 15 days ago

You can now orchestrate Fable 5, Sol, and any model inside Codex with one plugin. It's called Codex-Orchestration. Assign Fable 5 as the advisor, Sol as the executor, or any model to any role. Then define the order they work in. Codex handles the routing. I ran Fable 5 High as planner with GPT-5.6 Sol Extra High as executor on a set of issues Opus and GPT-5.5 always struggled with. Done in 30 minutes. 40% fewer limit hits. 2x faster implementation. Install it by pasting this into Codex: "Install Codex Orchestration: codex plugin marketplace add Cjbuilds/Codex-Orchestration codex plugin add codex-orchestration@codex-orchestration Verify the installation, then tell me to start a new task." Then assign your models: @ codex-orchestration advisor: Claude Fable 5 High, Executor: GPT-5.6 Sol High Open source. Tweak the routing however you want.
0:14

You can now orchestrate Fable 5, Sol, and any model inside Codex with one plugin. It's called Codex-Orchestration. Assign Fable 5 as the advisor, Sol as the executor, or any model to any role. Then define the order they work in. Codex handles the routing. I ran Fable 5 High as planner with GPT-5.6 Sol Extra High as executor on a set of issues Opus and GPT-5.5 always struggled with. Done in 30 minutes. 40% fewer limit hits. 2x faster implementation. Install it by pasting this into Codex: "Install Codex Orchestration: codex plugin marketplace add Cjbuilds/Codex-Orchestration codex plugin add codex-orchestration@codex-orchestration Verify the installation, then tell me to start a new task." Then assign your models: @ codex-orchestration advisor: Claude Fable 5 High, Executor: GPT-5.6 Sol High Open source. Tweak the routing however you want.

Alvaro Cintas

92,149 views • 2 months ago

this is f**king insane i cancelled my $20/mo claude subscription for this. a dev found a way around OpenAI's usage limits and got unlimited GPT-5.6 Luna on Codex for FREE ($0)😳 He built a three step local workflow on a single machine. This involved no servers, shared accounts, or a team. Instead he used a GitHub repo, one prompt file, and a local coding agent. Traditional users pay full price or hit usage limits. His cost: basically $0. Here's the set up (3min): → Repo layer: Installed 'sol-advisor' from GitHub. → Prompt layer: Copied the 'savings-prompt' out of the repo. → Agent layer: Pointed codex at gpt 5.6 luna with the prompt loaded. → Activation: Loaded it into codex. Usage limits gone. usage after activation: normal codex access. unlimited. one trick. one window. use this before it gets patched.
0:10

this is f**king insane i cancelled my $20/mo claude subscription for this. a dev found a way around OpenAI's usage limits and got unlimited GPT-5.6 Luna on Codex for FREE ($0)😳 He built a three step local workflow on a single machine. This involved no servers, shared accounts, or a team. Instead he used a GitHub repo, one prompt file, and a local coding agent. Traditional users pay full price or hit usage limits. His cost: basically $0. Here's the set up (3min): → Repo layer: Installed 'sol-advisor' from GitHub. → Prompt layer: Copied the 'savings-prompt' out of the repo. → Agent layer: Pointed codex at gpt 5.6 luna with the prompt loaded. → Activation: Loaded it into codex. Usage limits gone. usage after activation: normal codex access. unlimited. one trick. one window. use this before it gets patched.

painn

98,056 views • 1 month ago

ONE PROMPT. AN ENTIRE FINANCIAL DASHBOARD. I asked a new AI agent to build it, and it created this interactive dashboard from scratch. It planned the project, wrote the code, ran it locally, and handled the final touches. Meet EvoX Agent 🧵👇
0:19

ONE PROMPT. AN ENTIRE FINANCIAL DASHBOARD. I asked a new AI agent to build it, and it created this interactive dashboard from scratch. It planned the project, wrote the code, ran it locally, and handled the final touches. Meet EvoX Agent 🧵👇

gus

60,661 views • 10 days ago

It’s really satisfying when you can offer a native experience in React Native and encapsulate it for reuse. React Native is Native.
0:13

It’s really satisfying when you can offer a native experience in React Native and encapsulate it for reuse. React Native is Native.

Ferran

91,500 views • 10 months ago

Watched a 1.5 million dollar boat pull up to our dock yesterday & take on a few thousand dollars in fuel. The shit you see on this lake never ceases to amaze me, there’s no end to it. 💰 💵 🛥️ 🚤
0:15

Watched a 1.5 million dollar boat pull up to our dock yesterday & take on a few thousand dollars in fuel. The shit you see on this lake never ceases to amaze me, there’s no end to it. 💰 💵 🛥️ 🚤

David Bess

1,465,733 views • 2 months ago

The cheapest way to sell an app right now is a face and a screen I'm running it and the conversion is stupid It's one video doing two jobs → A reaction that buys you the first second → Your app running on the screen behind it Neither half has to explain the other That's the whole thing The screen recording never changes You only ever swap the reaction on top An account with 1,584 followers did 908K views and 66.5K saves with this Ten minutes of filming is a month of ads
0:14

The cheapest way to sell an app right now is a face and a screen I'm running it and the conversion is stupid It's one video doing two jobs → A reaction that buys you the first second → Your app running on the screen behind it Neither half has to explain the other That's the whole thing The screen recording never changes You only ever swap the reaction on top An account with 1,584 followers did 908K views and 66.5K saves with this Ten minutes of filming is a month of ads

Adrià Martinez

30,591 views • 1 month ago

Codex + 5.5 + computer use built me an iPhone shortcut to make it easy to use GPT Image 2 on any photo in my camera roll. Then it edited this screen recording with ffmpeg to speed it up so I could share it. Great for making quick UI mocks on my phone. And for lulz.
0:18

Codex + 5.5 + computer use built me an iPhone shortcut to make it easy to use GPT Image 2 on any photo in my camera roll. Then it edited this screen recording with ffmpeg to speed it up so I could share it. Great for making quick UI mocks on my phone. And for lulz.

Ilya Abyzov

45,451 views • 5 months ago

One of the top pieces of feedback we get about OpenAI Codex: “make it faster”. We addressed it in a big way with our ultra fast Codex-Spark model (research preview for Pro). Available in the latest Codex app, CLI, and IDE extension. Here’s Spark vs 5.3-Codex-Low side-by-side (Credit Romain Huet for the initial idea).
0:18

One of the top pieces of feedback we get about OpenAI Codex: “make it faster”. We addressed it in a big way with our ultra fast Codex-Spark model (research preview for Pro). Available in the latest Codex app, CLI, and IDE extension. Here’s Spark vs 5.3-Codex-Low side-by-side (Credit Romain Huet for the initial idea).

Derrick Choi

11,571 views • 7 months ago

You'll never find another artist like Seokjin. That man traveled over 36 hours to Argentina just to say goodbye to ARMY with only ONE song. I've never seen an artist do that for their fans. It was the most selfless act, and his kind heart never ceases to amaze me.
0:13

You'll never find another artist like Seokjin. That man traveled over 36 hours to Argentina just to say goodbye to ARMY with only ONE song. I've never seen an artist do that for their fans. It was the most selfless act, and his kind heart never ceases to amaze me.

134340 voy a ver a bts ⁷

49,554 views • 5 months ago

🤯 Still blows my mind how easy it is to call native APIs from #KotlinMultiplatform In this PR, I delegate to a native iOS 'bottom sheet' with a UIDatePicker, all written in Kotlin, and driven from Compose.
0:12

🤯 Still blows my mind how easy it is to call native APIs from #KotlinMultiplatform In this PR, I delegate to a native iOS 'bottom sheet' with a UIDatePicker, all written in Kotlin, and driven from Compose.

Chris Banes

61,265 views • 3 years ago

If you need to generate a target-specific wordlist, make sure to check out / XNL -н4cĸ3r (and @xnl-h4ck3r in the new Sky) GAP extension. It will scan for sus parameters and generate you a complete wordlist with one click of a button. See it in action 👇
0:14

If you need to generate a target-specific wordlist, make sure to check out / XNL -н4cĸ3r (and @xnl-h4ck3r in the new Sky) GAP extension. It will scan for sus parameters and generate you a complete wordlist with one click of a button. See it in action 👇

André Baptista

13,642 views • 9 months ago