正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Gemini can create applications that use Gemini. Gemini: "Make a working text adventure starship bridge simulator. there should be different stations to control & each should use AI in different ways to advance an overall story." "Make it better" (I cut out the loading screens)

Ethan Mollick

334,485 subscribers

128,102 次观看 • 1 年前 •via X (Twitter)

科学技术游戏教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Ethan Mollick 的头像

Ethan Mollick1 年前

Claude is supposed to do the same but I haven't gotten that to work yet. You can play the game here:

Ethan Mollick 的头像

Ethan Mollick1 年前

Ah, I had to turn it on in experimental features in Claude.... lets see what happens.

Ethan Mollick 的头像

Ethan Mollick1 年前

Okay, this is after a single prompt to Claude with AI on: "Make a working text adventure starship bridge simulator. there should be different stations to control, and each should use AI in different ways to advance an overall story using Claudeception"

Ryszard Szarfenberg 的头像

Ryszard Szarfenberg1 年前

I tried it in Claude, who created an educational game on logical fallacy recognition, where the AI was supposed to generate fallacious statements, but after some time Claude stated in the game itself that it was not ethical to generate fallacies.

🍓🍓🍓 的头像

🍓🍓🍓1 年前

yah it’s really useful as well. i think claude have just started doing this. you can start to see where this all could go.

Mark Attar 的头像

Mark Attar1 年前

Wow yea that looks pretty cool

Mark Attar 的头像

Mark Attar1 年前

Bespoke triple a level content and games will be fun

rohit 的头像

rohit1 年前

cli or web app?

NerdPropellant 的头像

NerdPropellant1 年前

That is mindblowing!

Tactical Bankroll 的头像

Tactical Bankroll1 年前

Gemini building Gemini inside Gemini? We’re officially in the sci-fi loop.

相关视频

Google is working on a native menu for Skills on Gemini desktop. These Skills may become available in all chats (fingers crossed). Users will be able to upload, create, and edit their Gemini Skills, as well as use Gemini to create them. Skill folders will also be available there, allowing users to select local folders containing the necessary Skills.

Google is working on a native menu for Skills on Gemini desktop. These Skills may become available in all chats (fingers crossed). Users will be able to upload, create, and edit their Gemini Skills, as well as use Gemini to create them. Skill folders will also be available there, allowing users to select local folders containing the necessary Skills.

🚨 AI News | TestingCatalog

204,534 次观看 • 2 个月前

Everyone is asking, “Which AI is better?” Wrong question. Gemini Pro 3.1 and Claude Sonnet 4.6 are built for different battles. Gemini wins when you need speed, scale, and multimodal power. Claude wins when logic, structure, and long-context reasoning actually matter. The real advantage? Knowing when to use each.

Everyone is asking, “Which AI is better?” Wrong question. Gemini Pro 3.1 and Claude Sonnet 4.6 are built for different battles. Gemini wins when you need speed, scale, and multimodal power. Claude wins when logic, structure, and long-context reasoning actually matter. The real advantage? Knowing when to use each.

Julian Goldie SEO

10,507 次观看 • 7 个月前

I found a Claude skill that plans my entire AI ad before I even open Gemini Omni. I just send it: → the product → the ad style (LEGO, crochet, cartoon, Pixar, etc.) that’s it. a few seconds later it gives me: → a complete script → a scene-by-scene breakdown → Gemini Omni prompts ready to generate I don’t waste time figuring out what each scene should look like or rewriting prompts until they work. I just generate the ad. It’s the exact workflow I’ve been using to make AI ads for affiliate offers, and it’s cut my creation time by more than half. RT + comment “SKILL” and I’ll DM you the exact workflow I use to make these ads (Claude skill included). (must be following for DM)

I found a Claude skill that plans my entire AI ad before I even open Gemini Omni. I just send it: → the product → the ad style (LEGO, crochet, cartoon, Pixar, etc.) that’s it. a few seconds later it gives me: → a complete script → a scene-by-scene breakdown → Gemini Omni prompts ready to generate I don’t waste time figuring out what each scene should look like or rewriting prompts until they work. I just generate the ad. It’s the exact workflow I’ve been using to make AI ads for affiliate offers, and it’s cut my creation time by more than half. RT + comment “SKILL” and I’ll DM you the exact workflow I use to make these ads (Claude skill included). (must be following for DM)

Bruno

58,858 次观看 • 1 个月前

Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️

Gemini 2.5 Flash can control a browser! Excited to share Gemini Browser Agent, a simple Python script example on how to use Google DeepMind Gemini 2.5 Flash and Browser Use to act as general assistant! 🤯 Usage Examples: 1⃣ Single Query Mode: `python scripts/gemini-browser-use.py --url --query "Summarize the key features of Gemini 2.5 Flash."` 2⃣Interactive Mode: Start an interactive session, optionally with a starting URL. `python scripts/gemini-browser-use.py` Command-line options: --model: The Gemini model to use (default: gemini-2.5-flash-preview-04-17) --headless: Run the browser in headless mode --url: Starting URL for the browser to navigate to before processing the query --query: Run a single query and exit (instead of interactive mode) Time to build a replication of Manus and OpenAI Operator powered by Gemini 2.5. Code below ⬇️

Philipp Schmid

105,308 次观看 • 1 年前

I used Gemini 3 to build a rough iOS app for competitive sleep tracking - built on the first try with zero bugs. Very impressive - other models have half a dozen issues that need debugging before they can be run on the simulator. Gemini got it working on the first try.

I used Gemini 3 to build a rough iOS app for competitive sleep tracking - built on the first try with zero bugs. Very impressive - other models have half a dozen issues that need debugging before they can be run on the simulator. Gemini got it working on the first try.

AI Breakfast

211,049 次观看 • 10 个月前

Google Veo 3.1 has an update! Using the Gemini App you can use multiple image references to create your final video. Combine this with a text prompt to keep consistency over characters or products. Here's how to do it.

Google Veo 3.1 has an update! Using the Gemini App you can use multiple image references to create your final video. Combine this with a text prompt to keep consistency over characters or products. Here's how to do it.

Jerrod Lew

39,491 次观看 • 8 个月前

Claude Opus 5 vs Gemini 4 vs GPT-6 Astra vs Grok 4.6 I handed the same unfinished drawing to four different AI models and said "be creative." Rumoured Gemini 4 checkpoint is inside Arena. four completely different pandas came out. and I genuinely can't pick a favorite 👇

Claude Opus 5 vs Gemini 4 vs GPT-6 Astra vs Grok 4.6 I handed the same unfinished drawing to four different AI models and said "be creative." Rumoured Gemini 4 checkpoint is inside Arena. four completely different pandas came out. and I genuinely can't pick a favorite 👇

Poonam Soni

37,910 次观看 • 5 天前

Gemini 3.1 Pro in Wonder is actually insane 🤯 All other models struggled turning a 1000+ layers design to dark mode, while Gemini figured out it can invert the colors that should stay the same (our pink branded colors and images) and applied an invert CSS function to the rest

Gemini 3.1 Pro in Wonder is actually insane 🤯 All other models struggled turning a 1000+ layers design to dark mode, while Gemini figured out it can invert the colors that should stay the same (our pink branded colors and images) and applied an invert CSS function to the rest

Aibek Yegemberdin

10,266 次观看 • 4 个月前

Fable 5.1: "Create the Catalog of Ships from the Iliad with a map, etc. i should be able to explore each accurate ship in 3D. there should be real images & archeological data i can draw on. test it with agents to make it accurate & beautiful, then revise"

Fable 5.1: "Create the Catalog of Ships from the Iliad with a map, etc. i should be able to explore each accurate ship in 3D. there should be real images & archeological data i can draw on. test it with agents to make it accurate & beautiful, then revise"

Ethan Mollick

74,557 次观看 • 21 天前

Better/faster/cheaper voice AI turn detection with Gemini 2.0 The code that determines when the agent should respond to the user is some of the most important code in your voice AI agent. The technical terms for this job are "turn detection" or "phrase endpointing." If the voice AI responds before the user has finished their thought, the conversation is choppy and unproductive. If the AI waits too long, the conversation is slow and frustrating. There are a number of ways to approach this. You can: 1. Use a fast "voice activity detection" model to detect pauses in speech. Respond when the user pauses. 2. Use a specialized phrase endpointing model that operates on transcribed text, pattern-matching on text semantics. 3. Train a specialized phrase endpointing model that operates directly on audio. 4. Leverage the native audio capabilities of a SOTA LLM like Gemini 2.0. We've benchmarked all four of these, and Gemini 2.0 currently beats other approaches. Using Gemini is also cheaper than transcribing the audio separately using a transcription service or model. Here's a short video showing Gemini phrase endpointing in two scenarios. First, correctly handling pauses in natural conversation. Second, requesting a phone number (which is a common activity in a use case like customer support). You can see the Completeness check lines in the terminal output, printed each time Gemini processes a chunk of audio.

Better/faster/cheaper voice AI turn detection with Gemini 2.0 The code that determines when the agent should respond to the user is some of the most important code in your voice AI agent. The technical terms for this job are "turn detection" or "phrase endpointing." If the voice AI responds before the user has finished their thought, the conversation is choppy and unproductive. If the AI waits too long, the conversation is slow and frustrating. There are a number of ways to approach this. You can: 1. Use a fast "voice activity detection" model to detect pauses in speech. Respond when the user pauses. 2. Use a specialized phrase endpointing model that operates on transcribed text, pattern-matching on text semantics. 3. Train a specialized phrase endpointing model that operates directly on audio. 4. Leverage the native audio capabilities of a SOTA LLM like Gemini 2.0. We've benchmarked all four of these, and Gemini 2.0 currently beats other approaches. Using Gemini is also cheaper than transcribing the audio separately using a transcription service or model. Here's a short video showing Gemini phrase endpointing in two scenarios. First, correctly handling pauses in natural conversation. Second, requesting a phone number (which is a common activity in a use case like customer support). You can see the Completeness check lines in the terminal output, printed each time Gemini processes a chunk of audio.

kwindla

64,190 次观看 • 1 年前

Gemini skills in Chrome are insanely powerful?! You can just write instructions and Gemini will be able to take any action over and over. 1. Create by typing "/" in the Gemini panel 2. Write your instructions 3. Type "/[skill-name]" And Gemini will automatically work for you by using the skill. So you can leverage it to - Scrap information - Take action in a specific web app - Anything you can perform in a browser basically Keep in mind that you can even use your emails or your Google account as a context... Which can be VERY useful.

Gemini skills in Chrome are insanely powerful?! You can just write instructions and Gemini will be able to take any action over and over. 1. Create by typing "/" in the Gemini panel 2. Write your instructions 3. Type "/[skill-name]" And Gemini will automatically work for you by using the skill. So you can leverage it to - Scrap information - Take action in a specific web app - Anything you can perform in a browser basically Keep in mind that you can even use your emails or your Google account as a context... Which can be VERY useful.

Paul Couvert

70,728 次观看 • 4 个月前

While most AI writing tools operate on plain text structured with Markdown, we’re teaching Gemini the underlying data model of Google Docs. By understanding Docs natively, Gemini generates and edits documents with full-fidelity formatting, fonts, and styles. That’s why when you ask Gemini to "match the format," it duplicates the exact structure— even clearing out the old text so you get a high quality, ready-to-use template instantly.

While most AI writing tools operate on plain text structured with Markdown, we’re teaching Gemini the underlying data model of Google Docs. By understanding Docs natively, Gemini generates and edits documents with full-fidelity formatting, fonts, and styles. That’s why when you ask Gemini to "match the format," it duplicates the exact structure— even clearing out the old text so you get a high quality, ready-to-use template instantly.

Google AI

32,937 次观看 • 6 个月前

ofc i had to add hand tracking to make this cat party more fun!! should i launch this lol, what kind of product should this be guys!! made with gemini and flow brief tutorial in the comment!

ofc i had to add hand tracking to make this cat party more fun!! should i launch this lol, what kind of product should this be guys!! made with gemini and flow brief tutorial in the comment!

danqi

13,546 次观看 • 4 个月前

The plot thickens. 🕵️ Use Gemini 2.5 Pro in the Google Gemini to turn random videos from your camera roll into a dramatic narrative. Try it yourself: 1️⃣ Go to Gemini and select “2.5 Pro” from the model dropdown. 2️⃣ Tap the plus icon and upload three videos from your camera roll. (Pro/Ultra subscribers, try using your Veo creations! 🎥) 3️⃣ Ask Gemini to write a short story based on the videos. Here’s our prompt to get you started: “Come up with a premise for an epic adventure based on these videos.”

The plot thickens. 🕵️ Use Gemini 2.5 Pro in the Google Gemini to turn random videos from your camera roll into a dramatic narrative. Try it yourself: 1️⃣ Go to Gemini and select “2.5 Pro” from the model dropdown. 2️⃣ Tap the plus icon and upload three videos from your camera roll. (Pro/Ultra subscribers, try using your Veo creations! 🎥) 3️⃣ Ask Gemini to write a short story based on the videos. Here’s our prompt to get you started: “Come up with a premise for an epic adventure based on these videos.”

Google

164,579 次观看 • 1 年前

I vibecoded an electron app for saving ALL THE PROMPTS you see on x or wherever on the internet. Would you want to use it? If yes, should I opensource it? Built in antigravity with gemini 3.1 pro btw :)

I vibecoded an electron app for saving ALL THE PROMPTS you see on x or wherever on the internet. Would you want to use it? If yes, should I opensource it? Built in antigravity with gemini 3.1 pro btw :)

Leon Lin

10,614 次观看 • 6 个月前

Joey Votto talking about choking up and how it helps him have more barrel control. Talking about trying to strike out less so he can be more consistent overall. I love the different club analogies. Can't only use a driver for game hitting; you have to use different clubs.

Joey Votto talking about choking up and how it helps him have more barrel control. Talking about trying to strike out less so he can be more consistent overall. I love the different club analogies. Can't only use a driver for game hitting; you have to use different clubs.

Xen Penny

64,893 次观看 • 2 年前