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.

Quality of life improvement in Gemini CLI ✨ You can now have model changes using /model persist to all future sessions. Hitting tab let's you toggle between only changing model for given session or all future sessions. This one was highly requested (should have had it a while ago... show more

Jack Wotherspoon

5,349 subscribers

13,211 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Gemini 2.5 Pro, our best coding model, is now available to all users! You can find it for free in the Gemini app as well as in Google AI Studio. Gemini Advanced users also now have access to it in Canvas mode. Cursor, @windsurf and Cline also added 2.5 Pro support this week!

Gemini 2.5 Pro, our best coding model, is now available to all users! You can find it for free in the Gemini app as well as in Google AI Studio. Gemini Advanced users also now have access to it in Canvas mode. Cursor, @windsurf and Cline also added 2.5 Pro support this week!

Addy Osmani

291,228 views • 1 year ago

been using a stealth model all day in opencode and it's working real well now you can use it too - it's called Sonic, it's made for coding and it's free for you to use so the team behind it can test it update to latest opencode and it should pop up right there

been using a stealth model all day in opencode and it's working real well now you can use it too - it's called Sonic, it's made for coding and it's free for you to use so the team behind it can test it update to latest opencode and it should pop up right there

dax

122,609 views • 9 months ago

People have always told you are beautiful and should be a model. Finally deciding to go for it and deciding to go on an interview you end up at a model casting. The boss isn't very impressed and tells you to go all the way. In need of money you hesitantly agree to it.

Sensitive content

People have always told you are beautiful and should be a model. Finally deciding to go for it and deciding to go on an interview you end up at a model casting. The boss isn't very impressed and tells you to go all the way. In need of money you hesitantly agree to it.

HurtCore 🔪

25,847 views • 11 months ago

✧ CHIBI MODEL GIVE4WAY ✧ I mentioned doing this a while ago as a way of giving back for all the support I've had recently, and I finally have the time to make it happen! Thank you all so much! Good luck! Entry is via Gleam 🔗↓

✧ CHIBI MODEL GIVE4WAY ✧ I mentioned doing this a while ago as a way of giving back for all the support I've had recently, and I finally have the time to make it happen! Thank you all so much! Good luck! Entry is via Gleam 🔗↓

Phlox Nesspalier 🪫📺

34,596 views • 1 month ago

Despite the mother of all sessions yesterday, Ampadu was still the first in for training this morning. Absolute model professional. My captain. #lufc

Despite the mother of all sessions yesterday, Ampadu was still the first in for training this morning. Absolute model professional. My captain. #lufc

MOT

856,208 views • 1 year ago

This robot arm = your AI model. One math number decides if it learns or completely breaks. This is Gradient Descent — the core math behind all of AI you are using in your day-to-day life.

This robot arm = your AI model. One math number decides if it learns or completely breaks. This is Gradient Descent — the core math behind all of AI you are using in your day-to-day life.

Mathematica

134,997 views • 2 months ago

Introducing your agent and the all-new Gemini Omni model in Google Flow. #GoogleIO ✨ Think of your agent as a creative partner. It reasons through complex tasks and helps you brainstorm, create, and edit, all while under your direction. ⚡ Gemini Omni is where Gemini’s intelligence meets our generative media models. Think of it as Nano Banana but for video. It is a major leap forward in world understanding, multimodality, and editing. Try all the latest Google Flow updates from I/O today at

Introducing your agent and the all-new Gemini Omni model in Google Flow. #GoogleIO ✨ Think of your agent as a creative partner. It reasons through complex tasks and helps you brainstorm, create, and edit, all while under your direction. ⚡ Gemini Omni is where Gemini’s intelligence meets our generative media models. Think of it as Nano Banana but for video. It is a major leap forward in world understanding, multimodality, and editing. Try all the latest Google Flow updates from I/O today at

Google Flow

167,620 views • 26 days ago

Gemini CLI now supports Session Management 🗃️ You can now pick up exactly where you left off! ✅ - Automatically saves all sessions ➡️ - Resume sessions with gemini --resume 🔍 - Run /resume to browse, filter and search past sessions Announcement blog below 👇

Gemini CLI now supports Session Management 🗃️ You can now pick up exactly where you left off! ✅ - Automatically saves all sessions ➡️ - Resume sessions with gemini --resume 🔍 - Run /resume to browse, filter and search past sessions Announcement blog below 👇

Jack Wotherspoon

23,550 views • 6 months ago

You can run Google new Gemma 4 on mobile easily. I am using Gemma 4 version E2B on my Pixel 10 Pro. Here is all you need to do: - Go to the App Store and install Google AI Edge Gallery. If you already have it, just update it. - From there, you can install the model directly and start using it. Still exploring what this small but powerful model can do :)

You can run Google new Gemma 4 on mobile easily. I am using Gemma 4 version E2B on my Pixel 10 Pro. Here is all you need to do: - Go to the App Store and install Google AI Edge Gallery. If you already have it, just update it. - From there, you can install the model directly and start using it. Still exploring what this small but powerful model can do :)

AshutoshShrivastava

226,336 views • 2 months ago

Co-founder John Collison says Stripe is betting on an agentic commerce future. Most purchases still happen in a browser but that’s changing. With MCP (Model Context Protocol), AI agents can transact directly inside the tools people already use. “It’s kind of funny... an AI can do everything for you, but you still have to manually enter the details. That is clearly not going to persist.”

Co-founder John Collison says Stripe is betting on an agentic commerce future. Most purchases still happen in a browser but that’s changing. With MCP (Model Context Protocol), AI agents can transact directly inside the tools people already use. “It’s kind of funny... an AI can do everything for you, but you still have to manually enter the details. That is clearly not going to persist.”

vitrupo

52,187 views • 1 year ago

You’re already training Big Tech’s AI models. So why aren’t you getting compensated for it? With Action Model you can download our browser extension and train AI passively in the background or by completing ActionFi tasks, while earning rewards and ownership in the model itself. This is what the future of AI should look like. Ownership back in the hands of the people who help build it, not billionaire control.

You’re already training Big Tech’s AI models. So why aren’t you getting compensated for it? With Action Model you can download our browser extension and train AI passively in the background or by completing ActionFi tasks, while earning rewards and ownership in the model itself. This is what the future of AI should look like. Ownership back in the hands of the people who help build it, not billionaire control.

Action Model

25,567 views • 2 months ago

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.

The founder of LangChain says both models and harnesses have gotten really good between December and now. According to Harrison Chase, the core idea of an agent before Christmas was a model running in a loop and calling tools. This had been the north star for 3 years. - langchain had this when it launched - autogpt was the same idea - openclaw is kind of a future version of it Then about a year ago, they started getting really good. Claude Code, Manus, and Deep Research were all launched around the same time. All of them use the same pattern: running in a loop with harnesses (planning tools, file systems, code execution, etc) Harness engineering became a thing. Then Opus came out in November and really unlocked it. - the harness let the model do more and more - less hardcoded logic - way more control Then everyone went on vacation, played around, and realized that the model and the harness finally worked reliably.

Ivan Burazin

33,948 views • 1 month ago

The kyutai fully end-to-end audio model demo of today is a huge deal that many people missed in the room Mostly irrelevant are the facts that: - they come a few week after OpenAI ChatGPT-4o - the demo was less polished than the 4o one (in terms of voice quality, voice timing…) Relevant: - the model training pipeline and model archi are simple and hugely scalable, with a tiny 8+ people team like Kyutai building it in 4 months. Synthetic data is a huge enabler here - laser focus on local devices: Moshi will soon be everywhere. Frontier model builders have low incentive to let you run smaller models locally (price per token…) but non-profits like Kyutai have very different incentives. The Moshi demo is already online while the OpenAI 4o one is still in limbo. - going under 300 ms of latency while keeping Llama 8B or above quality of answers is a key enabler in terms of interactivity, it’s game changing, This feeling when the model answer your question before you even finished asking is quite crazy or when you interrupt the model while it’s talking and it react… Predictive coding in a model, instantly updated model of what you’re about to say... Basically they nailed the fundamentals. It’s here. This interactive voice tech will be everywhere. It will soon be an obvious commodity.

The kyutai fully end-to-end audio model demo of today is a huge deal that many people missed in the room Mostly irrelevant are the facts that: - they come a few week after OpenAI ChatGPT-4o - the demo was less polished than the 4o one (in terms of voice quality, voice timing…) Relevant: - the model training pipeline and model archi are simple and hugely scalable, with a tiny 8+ people team like Kyutai building it in 4 months. Synthetic data is a huge enabler here - laser focus on local devices: Moshi will soon be everywhere. Frontier model builders have low incentive to let you run smaller models locally (price per token…) but non-profits like Kyutai have very different incentives. The Moshi demo is already online while the OpenAI 4o one is still in limbo. - going under 300 ms of latency while keeping Llama 8B or above quality of answers is a key enabler in terms of interactivity, it’s game changing, This feeling when the model answer your question before you even finished asking is quite crazy or when you interrupt the model while it’s talking and it react… Predictive coding in a model, instantly updated model of what you’re about to say... Basically they nailed the fundamentals. It’s here. This interactive voice tech will be everywhere. It will soon be an obvious commodity.

Thomas Wolf

339,446 views • 1 year ago

Merc with the Mouth! I still can't believe they brought him in all 3 roles?! It was a whole different adventure on this one. We made our own model to not wait for the game's release since acting sequences take a little bit longer to make and someone never shuts up! Hope you all enjoy it! Thank you Marvel Rivals for sponsoring this video!

Merc with the Mouth! I still can't believe they brought him in all 3 roles?! It was a whole different adventure on this one. We made our own model to not wait for the game's release since acting sequences take a little bit longer to make and someone never shuts up! Hope you all enjoy it! Thank you Marvel Rivals for sponsoring this video!

Sarp Serter

854,511 views • 4 months ago

Testing DeepSeek R1 in VSCode with CodeGPT Step-by-step guide to connect: ✨ Select "LLMs Cloud model" ✨ Choose DeepSeek as the provider ✨ Pick the "deepseek-reasoner" model ✨ Select code and/or files from your project and send them to the model That’s it! You’re all set to use this amazing DeepSeek model... 🚀 P.S.: Update to the latest version of CodeGPT to start using it!

Testing DeepSeek R1 in VSCode with CodeGPT Step-by-step guide to connect: ✨ Select "LLMs Cloud model" ✨ Choose DeepSeek as the provider ✨ Pick the "deepseek-reasoner" model ✨ Select code and/or files from your project and send them to the model That’s it! You’re all set to use this amazing DeepSeek model... 🚀 P.S.: Update to the latest version of CodeGPT to start using it!

Daniel San

34,346 views • 1 year ago

Think of Model Context Protocol as a USB port for your AI. 🔌 You can plug in documentation, tools, and context directly into Copilot CLI. Scott Hanselman 🌮 shows how to set it all up. 👇

Think of Model Context Protocol as a USB port for your AI. 🔌 You can plug in documentation, tools, and context directly into Copilot CLI. Scott Hanselman 🌮 shows how to set it all up. 👇

GitHub

44,242 views • 4 months ago

Today we’re taking a big step on the path toward AGI and releasing Gemini 3— our most intelligent model yet. With Gemini 3, you can bring any idea to life. It is state-of-the-art in reasoning, the best model in the world for multimodal understanding, and our best agentic and vibe coding model.

Today we’re taking a big step on the path toward AGI and releasing Gemini 3— our most intelligent model yet. With Gemini 3, you can bring any idea to life. It is state-of-the-art in reasoning, the best model in the world for multimodal understanding, and our best agentic and vibe coding model.

Google AI

492,732 views • 6 months ago

🇺🇸🇨🇺 Rubio on why Cuba is collapsing: "The only way Cuba is going to have a better future is if it has a different economic model. Their model doesn't work. It doesn't exist anywhere in the world."

🇺🇸🇨🇺 Rubio on why Cuba is collapsing: "The only way Cuba is going to have a better future is if it has a different economic model. Their model doesn't work. It doesn't exist anywhere in the world."

Mario Nawfal

74,372 views • 3 months ago

Daily #Blender Tip: If you have a model that fakes detail using a Normal map, it can be interesting to convert it to ‘real’ geometry that you can continue sculpting on, or for use in 3D printing. This shows you how to do it! #B3D

Daily #Blender Tip: If you have a model that fakes detail using a Normal map, it can be interesting to convert it to ‘real’ geometry that you can continue sculpting on, or for use in 3D printing. This shows you how to do it! #B3D

Jan van den Hemel

75,105 views • 3 years ago

new feature in opencode: warping never worry about whether or not you should work in a worktree again! now you can move sessions between worktrees and your local projects by warping them. it also brings any local changes with it!

new feature in opencode: warping never worry about whether or not you should work in a worktree again! now you can move sessions between worktrees and your local projects by warping them. it also brings any local changes with it!

James Long

122,510 views • 1 month ago