Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

DeepSeek V4 Flash vs GPT-5.6 Luna tested both models with the same prompt on highest reasoning > luna one shotted everything in under 3 mins in devin > v4 Flash needed an extra prompt to fix the movement and took over 5 mins in aihubmix cli which one do... show more

J A Z I I

7,529 subscribers

46,414 views • 5 days ago •via X (Twitter)

Science & Technology Education Gaming

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Codex can now run Deepseek-v4- flash! There's a catch though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇

Codex can now run Deepseek-v4- flash! There's a catch though. Deepseek's official setup switches your entire codex over to them, so your GPT models stop showing up at all. This is exactly what Codex Router is for. It adds models to the list instead of replacing them, so sol, grok, kimi and deepseek all sit in the same picker and i just grab whichever one suits the job. Deepseek v4-flash is $0.28 per million output tokens. opus 4.8 is $25. same picker, 89x apart. Links in the comment. setup's in the video 👇

Ziwen

93,988 views • 5 days ago

Kimi K3 beats GPT 5.6 Sol on both speed and in cost in backend bug fixing ! Planted 4 defects in the same Python order service: a wrong-total calculation, a broken access-control check (IDOR), a crash on invalid input, and an inventory oversell. Both models got identical code and the same prompt, with an automated test suite verifying every fix over the live API. Both went 4/4, but by the time Kimi K3 finished all 4, GPT 5.6 had only fixed 2. Kimi wrapped in under half the time, at half the cost. Kimi K3: 1min 34s · $0.1 · 4/4 GPT 5.6 Sol: 4min 6s · $0.2 · 4/4

Kimi K3 beats GPT 5.6 Sol on both speed and in cost in backend bug fixing ! Planted 4 defects in the same Python order service: a wrong-total calculation, a broken access-control check (IDOR), a crash on invalid input, and an inventory oversell. Both models got identical code and the same prompt, with an automated test suite verifying every fix over the live API. Both went 4/4, but by the time Kimi K3 finished all 4, GPT 5.6 had only fixed 2. Kimi wrapped in under half the time, at half the cost. Kimi K3: 1min 34s · $0.1 · 4/4 GPT 5.6 Sol: 4min 6s · $0.2 · 4/4

GMI Cloud

24,233 views • 15 days ago

AI agents can do animation for you now. All I did was create the character in GPT Image 2.0. Fable 5 handled the story and prompt, then I used Renoise CLI to run it with Seedance 2.0. Prompt in thread ⤵️

AI agents can do animation for you now. All I did was create the character in GPT Image 2.0. Fable 5 handled the story and prompt, then I used Renoise CLI to run it with Seedance 2.0. Prompt in thread ⤵️

Kiki

89,036 views • 13 days ago

Kimi K3 vs Claude Fables 5 Two models walked into a kitchen… and somehow made two completely different cookies. Which one are you taking a bite of? Prompt in the threads. 👇

Kimi K3 vs Claude Fables 5 Two models walked into a kitchen… and somehow made two completely different cookies. Which one are you taking a bite of? Prompt in the threads. 👇

Flowith

84,428 views • 14 days ago

AN ENTIRE PLAYABLE CYBERPUNK CITY FROM ONE SINGLE PROMPT → give Kimi K3 the idea and it builds you the whole city → move through the streets in 3D → neon lights, traffic, reactive buildings → all running in the browser $3 in API with K3. the same would run about $9 with Fable 5 this needed a full game studio a month ago

AN ENTIRE PLAYABLE CYBERPUNK CITY FROM ONE SINGLE PROMPT → give Kimi K3 the idea and it builds you the whole city → move through the streets in 3D → neon lights, traffic, reactive buildings → all running in the browser $3 in API with K3. the same would run about $9 with Fable 5 this needed a full game studio a month ago

z

55,164 views • 14 days ago

Claude Opus 4.6 is available for all users in Orchids right now! Tag Orchids with any app idea and we’ll give you 100k in free credits to test it out. Comparisons to Opus 4.5, GPT-5.2-Codex, Gemini 3 Flash, and Kimi K2.5 👇 Prompt: Make me an interactive, 3d model of the solar system.

Claude Opus 4.6 is available for all users in Orchids right now! Tag Orchids with any app idea and we’ll give you 100k in free credits to test it out. Comparisons to Opus 4.5, GPT-5.2-Codex, Gemini 3 Flash, and Kimi K2.5 👇 Prompt: Make me an interactive, 3d model of the solar system.

Orchids

22,774 views • 6 months ago

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

🚨Gemini 3.6 Flash is trash I tested it on a 3D Golden Gate Bridge, and the results were awful. • I had to re-prompt it three times because it repeatedly ignored the instructions. • First attempt, instead of creating the requested .html file, it first tried to build the experience inside the Gemini app using simulations. • Then second attempt it started placing images from the web into the chat rather than actually producing the file. • Even after getting it to complete the task, the final output was dramatically worse than Gemini 3.1 Pro, which is 5 months old and now not even a top 10 model on leaderboards. This feels like a regression from Gemini 3.5 Flash and honestly, it is one of the weakest models I have tested in the past few months. Has anyone else tested Gemini 3.6 Flash yet, and are you seeing the same thing?

Lumina

72,113 views • 14 days ago

this video is 100% AI made with one prompt in 2 mins using my own system, prompt to final video AI UGC yappers are fast to make, scalable, and can be automated (as much as today’s technology allows) and what's best it can be used to sell everything: - ecom - digital products - saas - supplements anything and everything... the real UGC industry isn't dying, it already died

this video is 100% AI made with one prompt in 2 mins using my own system, prompt to final video AI UGC yappers are fast to make, scalable, and can be automated (as much as today’s technology allows) and what's best it can be used to sell everything: - ecom - digital products - saas - supplements anything and everything... the real UGC industry isn't dying, it already died

MAX

78,212 views • 4 months ago

🚀 New Video Alert – GPT-5 in Copilot Studio! GPT-5 has officially arrived in Microsoft Copilot Studio, and I couldn’t resist putting it to the test. In this video, I explore: 🔍 GPT-5 Auto & GPT-5 Reasoning models for custom agents. 🛠 How I leveraged GPT-5 Chat inside a custom prompt for more tailored outputs. ⚖️ GPT-5 Chat Vs. GPT-4.1 to highlight improvements and trade-offs If you’ve been wondering what GPT-5 brings to Copilot Studio—this video is packed with real examples, practical tests, and insights to help you understand what these new experimental models have to offer. 🎥 Watch here: #CopilotStudio #GPT5 #AIBuilder #MicrosoftCopilot #LowCodeAI #OpenAI #AI #CopilotStudio #GPT5Auto #GPT5Reasoning #GPT5Chat

🚀 New Video Alert – GPT-5 in Copilot Studio! GPT-5 has officially arrived in Microsoft Copilot Studio, and I couldn’t resist putting it to the test. In this video, I explore: 🔍 GPT-5 Auto & GPT-5 Reasoning models for custom agents. 🛠 How I leveraged GPT-5 Chat inside a custom prompt for more tailored outputs. ⚖️ GPT-5 Chat Vs. GPT-4.1 to highlight improvements and trade-offs If you’ve been wondering what GPT-5 brings to Copilot Studio—this video is packed with real examples, practical tests, and insights to help you understand what these new experimental models have to offer. 🎥 Watch here: #CopilotStudio #GPT5 #AIBuilder #MicrosoftCopilot #LowCodeAI #OpenAI #AI #CopilotStudio #GPT5Auto #GPT5Reasoning #GPT5Chat

Daniel Christian

14,705 views • 1 year ago

🐐 Gemini 3 Pro GA One shot prompt is in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted this

🐐 Gemini 3 Pro GA One shot prompt is in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted this

Chetaslua

35,579 views • 5 months ago

AI motion capture is taking over vfx completely you can copy fast body motion, expression, lips.. and paste on other actors bg, costume, looks and everything in the scene are editable here's how to do it in 5 mins:

AI motion capture is taking over vfx completely you can copy fast body motion, expression, lips.. and paste on other actors bg, costume, looks and everything in the scene are editable here's how to do it in 5 mins:

el.cine

89,729 views • 6 months ago

I tested Kimi K3 vs Claude Opus 4.8 Same prompt, an armory bay with lighting, props, and detail. Top is Kimi K3, bottom is Opus 4.8. It's not even close. Kimi K3 built a full scene with textures, proper lighting, ammo crates, weapon racks, working detail everywhere. Opus 4.8 gave me a near empty room with a couple of floating tables. No doubt it beats Opus 4.8. Kimi K3 is Fable 5 level, and it's clearly better than GPT-5.6 Sol at 3D and games. An open weight model just matched the best closed models on the market. Let that sink in.

I tested Kimi K3 vs Claude Opus 4.8 Same prompt, an armory bay with lighting, props, and detail. Top is Kimi K3, bottom is Opus 4.8. It's not even close. Kimi K3 built a full scene with textures, proper lighting, ammo crates, weapon racks, working detail everywhere. Opus 4.8 gave me a near empty room with a couple of floating tables. No doubt it beats Opus 4.8. Kimi K3 is Fable 5 level, and it's clearly better than GPT-5.6 Sol at 3D and games. An open weight model just matched the best closed models on the market. Let that sink in.

Bhavy☄️

468,355 views • 19 days ago

We tested a lot of design skills in Codex and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.

We tested a lot of design skills in Codex and other AI agents. They fix the old AI slop. But they often create a new one: the “taste skill look.” - Same premium sections. - Same editorial typography. - Same generated-design smell. Open Design does not rely on one taste prompt. It combines skills, systems, critique loops, and local harnesses to make AI pages feel less generated and more designed. This page was generated directly in Open Design.

Open Design

44,061 views • 2 months ago

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

Right now, you may not have access to models like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.

Alok

65,251 views • 1 month ago

Followed up on the same idea to create this clip. Started with a single frame from Krea 2, used GPT Image 2 to create the 3x3 contact sheet preserving the same aesthetic and dropped both into Seedance 2. Some flaws in the final clip but I think the aesthetic holds pretty well from the original image to the seedance gen. Krea 2 → GPT Image 2 → Seedance 2 was all done within Krea seedance prompt in the next post 👇

Followed up on the same idea to create this clip. Started with a single frame from Krea 2, used GPT Image 2 to create the 3x3 contact sheet preserving the same aesthetic and dropped both into Seedance 2. Some flaws in the final clip but I think the aesthetic holds pretty well from the original image to the seedance gen. Krea 2 → GPT Image 2 → Seedance 2 was all done within Krea seedance prompt in the next post 👇

V

76,555 views • 2 months ago

Code Interpreter in ChatGPT is incredible! Took me 5 mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"

Code Interpreter in ChatGPT is incredible! Took me 5 mins to make this game. You can make your own game assets with any AI generator and then ask GPT-4 with Code Interpreter to write code. If you have any problems you can ask it to fix the errors. 1. Write this prompt: "write p5.js code for Asteroids where you control a spaceship with the mouse and shoot asteroids with the left click of the mouse. If your spaceship collides with an asteroid, you lose. If you shoot down all asteroids, you win! I want to use my own textures for the spaceship and for asteroids." 2. Go to Openprocessing website create and save sketch (you'll need to save it before uploading any texture files). Copy paste code from GPT-4 3. Generate texture files and remove backgrounds, for example in Clip Drop 4. Replace names of files with your filenames 5. Run the program 6. If something doesn't work ask GPT-4 to fix it (you can copy an error and paste in GPT-4) like you would ask a human programmer 7. To learn a bit of programming write these prompts to GPT-4: "Act as my programming teacher. Tell me an algorithm of Asteroids game in detail and make names of functions and explain what each of these functions will do. Don't write the code just yet." and then " Can you describe the algorithm overall for a 10-year-old child"

Kris Kashtanova

1,674,852 views • 3 years ago

There's a FREE public endpoint for deepseek v4 flash 0731 😳 no account or no card needed, just a url victormustar from hugging face made it. openai-compatible chat completions. anyone can use it. what you get for $0: -82.7 terminal-bench (opus 4.8 is ~85) -swe-bench 54.4 — 7.3 before the update -1M context, thinking mode, tool calling -no signup, no key, no billing what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -Cursor: $20/mo all for $0 how to set it up: 1. base url: 2. model: deepseek-ai/DeepSeek-V4-Flash-0731 3. api key: anything Works in Hermes, Cursor, OpenCode, Aider, Cline, Claude Code (via proxy), and any OpenAI tool Important: ~12 req/min per IP. shared box. be nice. use this before it gets popular

There's a FREE public endpoint for deepseek v4 flash 0731 😳 no account or no card needed, just a url victormustar from hugging face made it. openai-compatible chat completions. anyone can use it. what you get for $0: -82.7 terminal-bench (opus 4.8 is ~85) -swe-bench 54.4 — 7.3 before the update -1M context, thinking mode, tool calling -no signup, no key, no billing what this replaces: -Claude Opus 4.8: $15/M in, $75/M out -Cursor: $20/mo all for $0 how to set it up: 1. base url: 2. model: deepseek-ai/DeepSeek-V4-Flash-0731 3. api key: anything Works in Hermes, Cursor, OpenCode, Aider, Cline, Claude Code (via proxy), and any OpenAI tool Important: ~12 req/min per IP. shared box. be nice. use this before it gets popular

painn

79,872 views • 4 days ago

> A mere 5 months later with Gemini 3 Pro and GPT-5.1 it is not clear that Anthropic has any material lead in coding anymore The evil one is defeated. Peace has been restored to the planet.

> A mere 5 months later with Gemini 3 Pro and GPT-5.1 it is not clear that Anthropic has any material lead in coding anymore The evil one is defeated. Peace has been restored to the planet.

Lincoln 🇿🇦

128,841 views • 8 months ago

This took 5 minutes. The entire deck was made by AI. It lets you turn a rough prompt into a full presentation in seconds... with clean layouts, on-brand design and perfect structure. Let me show you the process to do it: ↓

EyeingAI

31,446 views • 8 months ago