Loading video...

Video Failed to Load

Go Home

LLMs struggle at RTS games because there's a significant lag between seeing and acting. They effectively play it turn-based. But can you overcome this with the right tools and prompts? This is Gemini 3.5 Flash batching multiple actions into a single response

lefthanddraft's profile picture

Wyatt Walls

13,548 subscribers

34,146 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Build a jet lag strategy for your next trip with Gemini 3.5 Flash. Gemini can grab your flight itinerary from Gmail, build a custom sleep schedule based on your time zone, and add it right to your calendar for helpful reminders.
0:28

Build a jet lag strategy for your next trip with Gemini 3.5 Flash. Gemini can grab your flight itinerary from Gmail, build a custom sleep schedule based on your time zone, and add it right to your calendar for helpful reminders.

Google Gemini

35,759,771 views • 3 months ago

Following our Gemini 3.5 Flash launch at #GoogleIO, check out this demo of what it can do right inside the Gemini app. Watch 3.5 Flash build an interactive circuit helper, outputting a step-by-step physical build guide alongside a working simulation. It’s a great example of how the Gemini app can help students learn visually, breaking down new or complex concepts and guiding them through hands-on subjects interactively. 3.5 Flash is available globally today!
0:59

Following our Gemini 3.5 Flash launch at #GoogleIO, check out this demo of what it can do right inside the Gemini app. Watch 3.5 Flash build an interactive circuit helper, outputting a step-by-step physical build guide alongside a working simulation. It’s a great example of how the Gemini app can help students learn visually, breaking down new or complex concepts and guiding them through hands-on subjects interactively. 3.5 Flash is available globally today!

koray kavukcuoglu

59,678 views • 4 months ago

If you use LLMs, this is fascinating. Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭’s LeakHub collects leaked system prompts from AI models, agents and tools. So you can see the hidden instructions shaping every response. Understand the inputs = control the outputs. Check it out:
0:34

If you use LLMs, this is fascinating. Pliny the Liberator 🐉󠅫󠄼󠄿󠅆󠄵󠄐󠅀󠄼󠄹󠄾󠅉󠅭’s LeakHub collects leaked system prompts from AI models, agents and tools. So you can see the hidden instructions shaping every response. Understand the inputs = control the outputs. Check it out:

The OSINT Newsletter

15,694 views • 7 months ago

Fast enough to play games ⚡️ We challenged Gemini 3 Flash to a quick drawing game in the G3mini. Because this model is optimized for speed, it can see and guess what you’re drawing while you’re still sketching it.
0:22

Fast enough to play games ⚡️ We challenged Gemini 3 Flash to a quick drawing game in the G3mini. Because this model is optimized for speed, it can see and guess what you’re drawing while you’re still sketching it.

Google

119,117 views • 8 months ago

I built a lightweight meeting notes assistant with Hermes + StepFun’s Step Plan. Step Plan is a subscription-based AI service that lets developers use StepFun models like Step 3.5 Flash cost-effectively across coding tools and agent platforms. For this demo, you paste in messy meeting notes. It gives you back a clean summary, action items, risks, deadlines, and follow-up copy. Simple idea, but genuinely useful.
0:55

I built a lightweight meeting notes assistant with Hermes + StepFun’s Step Plan. Step Plan is a subscription-based AI service that lets developers use StepFun models like Step 3.5 Flash cost-effectively across coding tools and agent platforms. For this demo, you paste in messy meeting notes. It gives you back a clean summary, action items, risks, deadlines, and follow-up copy. Simple idea, but genuinely useful.

ares. 🎧

41,185 views • 3 months ago

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)
1:09

You can just take academic papers and paste them into Gemini 2.5/ChatGPT o3/Claude 4 with the prompt "build me a game based on this paper, make it interesting and thematic but still conveying key findings" and get a tiny working educational game. (In this case, I used Gemini)

Ethan Mollick

137,469 views • 1 year ago

i should never be sharing this but f*ck it Seedance + GPT Images 2 is insane for AI video you can generate ads for almost any product, even really complex ones that Omni or Kling struggle to create without issues i've been using this for videos with complicated movements, multiple actions, and comedy scenes, and it's been perfect for it here's what you can do with it: - create realistic product ads with complex movements or product looks - generate consistent characters across multiple scenes - pull off comedy skits with natural actions and timing - animate almost any product without weird AI artifacts - turn a single image into a high-quality ad in minutes i put together a step-by-step breakdown on how i create them, with all the prompts and everything i'm using - literally my complete workflow RT + reply "SEEDANCE" and i'll send it over (must follow so i can DM)
0:37

i should never be sharing this but f*ck it Seedance + GPT Images 2 is insane for AI video you can generate ads for almost any product, even really complex ones that Omni or Kling struggle to create without issues i've been using this for videos with complicated movements, multiple actions, and comedy scenes, and it's been perfect for it here's what you can do with it: - create realistic product ads with complex movements or product looks - generate consistent characters across multiple scenes - pull off comedy skits with natural actions and timing - animate almost any product without weird AI artifacts - turn a single image into a high-quality ad in minutes i put together a step-by-step breakdown on how i create them, with all the prompts and everything i'm using - literally my complete workflow RT + reply "SEEDANCE" and i'll send it over (must follow so i can DM)

MAX

10,900 views • 1 month ago

As you can see we're both moving and ghosted bottom right, a single UAV is popped and all three of us appear on the radar from it. Regardless, they may have known the play we were making but how are we competing in this game with a bug this broken?
0:22

As you can see we're both moving and ghosted bottom right, a single UAV is popped and all three of us appear on the radar from it. Regardless, they may have known the play we were making but how are we competing in this game with a bug this broken?

Tommey

242,074 views • 2 years ago

It’s honestly wild what GPT-2 and Seedance 2.0 can create right now, and this is exactly the kind of AI content you can use to monetize. You can turn this into income through faceless YouTube channels or TikTok pages—no camera, no crew, no complicated setup. Just AI tools, smart prompts, and a clear idea, and you’re already building content that can make money online.
1:59

It’s honestly wild what GPT-2 and Seedance 2.0 can create right now, and this is exactly the kind of AI content you can use to monetize. You can turn this into income through faceless YouTube channels or TikTok pages—no camera, no crew, no complicated setup. Just AI tools, smart prompts, and a clear idea, and you’re already building content that can make money online.

Isabella

16,439 views • 3 months ago

this is a crypto game and you can play it right now
0:33

this is a crypto game and you can play it right now

Star Atlas

86,075 views • 1 year ago

Drywall work can be a difficult job but with the right tools and experience it can be done right . Do you like it.
1:02

Drywall work can be a difficult job but with the right tools and experience it can be done right . Do you like it.

🔨Robert The Builder 🇺🇸

109,896 views • 5 months ago

I built and open-sourced a repo to turn hours of cycling GoPro footage into a 60-second highlight reel with ride telemetry burned in. Every second of the ride is scanned by gemini-3.5-flash, as is the clip ranking + curation. The whole thing costs about $0.04 per ride and takes 10 minutes. Here's what I've learned about teaching LLMs taste over 1000 miles and 180,430 seconds + frames processed through this pipeline.
1:03

I built and open-sourced a repo to turn hours of cycling GoPro footage into a 60-second highlight reel with ride telemetry burned in. Every second of the ride is scanned by gemini-3.5-flash, as is the clip ranking + curation. The whole thing costs about $0.04 per ride and takes 10 minutes. Here's what I've learned about teaching LLMs taste over 1000 miles and 180,430 seconds + frames processed through this pipeline.

Ian Macomber

62,706 views • 2 months ago

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.
0:33

Audio Transcription with Google Gemini 1.5 Flash In this video, Gemini-Flash was able to transcribe 13 minutes of audio in 50-60 seconds. I have tested this with multiple audio files, and the transcription accuracy is close to 99%. If the audio is clear, you get 100% correct transcription. Even if the audio is really bad with a lot of noise, you still get around 95-96% accuracy. The code for this is available on GitHub. If you're interested, you can download and run it. You just need a Google API key.

AshutoshShrivastava

123,044 views • 2 years ago

GEMINI 3 LAUNCH IS HERE I got a SNEAK PEEK at Gemini 3 with Logan Kilpatrick (Google Deepmind), and it might be the most POWERFUL vibe-coding tool on the planet. A little breakdown: 1. Anyone can build 3D and casual games now You can vibecode full, playable 3D video games generated in minutes. Actual games with physics, characters, controls, and loops you can remix instantly. Pure insanity. I can see founders and brands spinning up games on the fly to ride trends and drive growth. 2. Intelligent apps are becoming the default We built apps where reasoning, memory, and multi-step planning were baked in from the start. Once you’re building apps with ACTUAL intelligence baked in, there’s a whole wave of new opportunities that weren’t possible before. 3. Gemini acts like a creative partner You describe the idea, Gemini fills in the gaps, challenges decisions, proposes alternatives, and iterates in real time. 4. Vibe coding hits a new level Gemini 3 can generate assets, code, game logic, UI, and narrative in one flow. Tools like Claude and Cursor feel fast. This feels like the next layer, the one where a single builder can compete with full teams. Logan Kilpatrick and I pushed Google Gemini 3 hard, and the outputs were solid. A few times we had to give it a few extra prompts but it took feedback really well. I think 1 year ago, a lot of people discounted Google in the AI arms race. Can you discount them anymore? Doubt it. After this, it feels like they at best leading, at worst leading. What do you think of Google's AI efforts/Gemini 3 My biggest takeaway was how it just felt like Gemini 3 had a little more vibe coding horsepower than anything I’ve used.
39:03

GEMINI 3 LAUNCH IS HERE I got a SNEAK PEEK at Gemini 3 with Logan Kilpatrick (Google Deepmind), and it might be the most POWERFUL vibe-coding tool on the planet. A little breakdown: 1. Anyone can build 3D and casual games now You can vibecode full, playable 3D video games generated in minutes. Actual games with physics, characters, controls, and loops you can remix instantly. Pure insanity. I can see founders and brands spinning up games on the fly to ride trends and drive growth. 2. Intelligent apps are becoming the default We built apps where reasoning, memory, and multi-step planning were baked in from the start. Once you’re building apps with ACTUAL intelligence baked in, there’s a whole wave of new opportunities that weren’t possible before. 3. Gemini acts like a creative partner You describe the idea, Gemini fills in the gaps, challenges decisions, proposes alternatives, and iterates in real time. 4. Vibe coding hits a new level Gemini 3 can generate assets, code, game logic, UI, and narrative in one flow. Tools like Claude and Cursor feel fast. This feels like the next layer, the one where a single builder can compete with full teams. Logan Kilpatrick and I pushed Google Gemini 3 hard, and the outputs were solid. A few times we had to give it a few extra prompts but it took feedback really well. I think 1 year ago, a lot of people discounted Google in the AI arms race. Can you discount them anymore? Doubt it. After this, it feels like they at best leading, at worst leading. What do you think of Google's AI efforts/Gemini 3 My biggest takeaway was how it just felt like Gemini 3 had a little more vibe coding horsepower than anything I’ve used.

GREG ISENBERG

73,838 views • 10 months ago

You don’t need a title change to build apps. If you have an idea and curiosity, you can turn prompts into live applications with AI Studio + Google Cloud. Explore our new collection of guides covering web apps, games, spatial AI tools, and mobile apps →
1:05

You don’t need a title change to build apps. If you have an idea and curiosity, you can turn prompts into live applications with AI Studio + Google Cloud. Explore our new collection of guides covering web apps, games, spatial AI tools, and mobile apps →

Google Cloud Tech

70,271 views • 25 days ago

Playing Pokemon with LLMs became a benchmark, but what about Super Mario? Turns out Google DeepMind Gemini 2.0 Flash can play Super Mario in real-time due to its fast latency, multimodal input and long context! 🎮 Gemini 2.0 Flash receives screenshots of the game and then generates Python code (PyAutoGUI commands) for each screenshot to control the game for a short period (the next 1 or 2 seconds). Add a while loop to it and you have it play in real-time. 🤯
1:15

Playing Pokemon with LLMs became a benchmark, but what about Super Mario? Turns out Google DeepMind Gemini 2.0 Flash can play Super Mario in real-time due to its fast latency, multimodal input and long context! 🎮 Gemini 2.0 Flash receives screenshots of the game and then generates Python code (PyAutoGUI commands) for each screenshot to control the game for a short period (the next 1 or 2 seconds). Add a while loop to it and you have it play in real-time. 🤯

Philipp Schmid

153,097 views • 1 year ago

JB Pritzker: “Trump’s treasonous words are leading to treasonous actions. Pushing back at authoritarian regimes starts with a resistance that can effectively ridicule the opposition and look into the camera and say this guy is full of shit”
0:43

JB Pritzker: “Trump’s treasonous words are leading to treasonous actions. Pushing back at authoritarian regimes starts with a resistance that can effectively ridicule the opposition and look into the camera and say this guy is full of shit”

Marco Foster

90,578 views • 11 months ago