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。

Introducing Vibe Coding XR, a new rapid prototyping workflow that empowers Gemini Canvas w/ the XR Blocks framework to turn user prompts into interactive, physics-aware WebXR applications, allowing creators to quickly test intelligent spatial experiences →

Google Research

104,383 subscribers

227,455 次观看 • 4 个月前 •via X (Twitter)

教育新闻政治科学技术

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

📢Introducing Generated Reality📢 A world model for XR that turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4

📢Introducing Generated Reality📢 A world model for XR that turns your tracked hand and head poses into an interactive, generative video experience. Take world models to the next level by interacting with the world using your own body! 🔗 1/4

Gordon Wetzstein

20,045 次观看 • 5 个月前

We translated the endurance of competitive hot dog eating into a game by prompting Gemini to “Create a HTML, CSS, Javascript hot dog eating contest game. Game mechanics is user needs to click super fast to eat each hotdog. Add a glass of water to help digest and allowing for faster eating when a user eats too many hotdogs. Timer is 1 minute.“ The Google Gemini App built the game mechanics in a single prompt, so the rest of our vibe coding focused on refining UI design with Gemini. Play here:

We translated the endurance of competitive hot dog eating into a game by prompting Gemini to “Create a HTML, CSS, Javascript hot dog eating contest game. Game mechanics is user needs to click super fast to eat each hotdog. Add a glass of water to help digest and allowing for faster eating when a user eats too many hotdogs. Timer is 1 minute.“ The Google Gemini App built the game mechanics in a single prompt, so the rest of our vibe coding focused on refining UI design with Gemini. Play here:

Google AI

31,465 次观看 • 1 年前

To build the next major leap in spatial computing, you can't rely on standard hardware architecture. That’s why we partnered with Snapdragon. We are incredibly proud to announce that the new XREAL AURA is the world’s first device powered by the new Snapdragon Reality Elite platform. To deliver an industry-leading 70° FOV and real-time processing, we utilized a revolutionary split-compute dual-chip architecture. By pairing the Snapdragon Reality Elite with XREAL’s custom X1S co-processor, we efficiently distribute the processing load. The X1S handles sensor fusion and spatial mapping at the edge, freeing the Snapdragon chip to run Android XR and GeminiI at absolute maximum performance without thermal throttling. The result? The most immersive XR experience ever engineered into a portable form factor. At just under 95g, you get the performance of a high-end spatial computer in a glasses form factor you can actually wear all day. Secure your spot in the next generation of XR: Reserve the XREAL AURA now for USD 99 and receive a USD 199 credit toward your final purchase at launch. 🔗 Reserve Yours Now:

To build the next major leap in spatial computing, you can't rely on standard hardware architecture. That’s why we partnered with Snapdragon. We are incredibly proud to announce that the new XREAL AURA is the world’s first device powered by the new Snapdragon Reality Elite platform. To deliver an industry-leading 70° FOV and real-time processing, we utilized a revolutionary split-compute dual-chip architecture. By pairing the Snapdragon Reality Elite with XREAL’s custom X1S co-processor, we efficiently distribute the processing load. The X1S handles sensor fusion and spatial mapping at the edge, freeing the Snapdragon chip to run Android XR and GeminiI at absolute maximum performance without thermal throttling. The result? The most immersive XR experience ever engineered into a portable form factor. At just under 95g, you get the performance of a high-end spatial computer in a glasses form factor you can actually wear all day. Secure your spot in the next generation of XR: Reserve the XREAL AURA now for USD 99 and receive a USD 199 credit toward your final purchase at launch. 🔗 Reserve Yours Now:

XREAL 👓

21,125 次观看 • 1 个月前

Made a quick haptic feedback prototype for hand-tracking interactions with a voxel. Felt fun and engaging. It's another level of immersiveness (unfortunately, the video is not able to convey this). Visual design alone can make an interactive experience great, but if you want to make it exceptional, DIFFERENT, this is where haptic design plays the key role. The device on my wrist is from the Hapticlabs.io Prototyping Kit (the thing on my index fingertip is called Linear Resonant Actuator). It's a beautiful, simple-to-use tool. Found a good case for it in my experiments :) To get hand-tracking data, I used the Leap Motion controller (Computer Vision Camera), which is excellent for quick prototypes like this. I saw people experimenting with gloves to build a solid haptic feedback system for XR. It's great for advanced immersive experiences (video games/simulators/interactive entertainment). But for many day-to-day use cases (productivity/OS/media entertainment), having just a "simple" thimble that provides the haptic feedback for the "touching" fingertip will already significantly improve the UX. Hope we will have something like this from our major XR vendors in the near future.

Made a quick haptic feedback prototype for hand-tracking interactions with a voxel. Felt fun and engaging. It's another level of immersiveness (unfortunately, the video is not able to convey this). Visual design alone can make an interactive experience great, but if you want to make it exceptional, DIFFERENT, this is where haptic design plays the key role. The device on my wrist is from the Hapticlabs.io Prototyping Kit (the thing on my index fingertip is called Linear Resonant Actuator). It's a beautiful, simple-to-use tool. Found a good case for it in my experiments :) To get hand-tracking data, I used the Leap Motion controller (Computer Vision Camera), which is excellent for quick prototypes like this. I saw people experimenting with gloves to build a solid haptic feedback system for XR. It's great for advanced immersive experiences (video games/simulators/interactive entertainment). But for many day-to-day use cases (productivity/OS/media entertainment), having just a "simple" thimble that provides the haptic feedback for the "touching" fingertip will already significantly improve the UX. Hope we will have something like this from our major XR vendors in the near future.

Oleg Frolov

35,579 次观看 • 8 个月前

If I had 60 days to make my first $10k online, this is exactly what I’d do. not dropshipping. not SMMA. not copywriting. i’d combine Claude, Gemini Omni, and affiliate marketing. here’s the workflow: → find a high-converting eCommerce offer on Glitchy → use Claude to write a script around the product’s biggest pain point → turn that script into an animated AI ad with Gemini Omni → test multiple hooks organically on TikTok → scale the winners. the biggest advantage isn’t that Gemini Omni makes incredible videos. it’s that it makes AI ad creation cheap enough for beginners to compete. when creating ads costs almost nothing, testing becomes your unfair advantage. rt + comment “omni” and i’ll send you the exact workflow. (must be following for dm)

If I had 60 days to make my first $10k online, this is exactly what I’d do. not dropshipping. not SMMA. not copywriting. i’d combine Claude, Gemini Omni, and affiliate marketing. here’s the workflow: → find a high-converting eCommerce offer on Glitchy → use Claude to write a script around the product’s biggest pain point → turn that script into an animated AI ad with Gemini Omni → test multiple hooks organically on TikTok → scale the winners. the biggest advantage isn’t that Gemini Omni makes incredible videos. it’s that it makes AI ad creation cheap enough for beginners to compete. when creating ads costs almost nothing, testing becomes your unfair advantage. rt + comment “omni” and i’ll send you the exact workflow. (must be following for dm)

Bruno

21,631 次观看 • 19 天前

That dog in your photo? He's got something to say. 🐶 Turn your images into eight-second video clips with sound effects and speech in the Google Gemini and Flow from Google Labs. This feature uses Veo 3 to generate motion that reflects real world physics and includes a new experimental audio capability so you can really bring your images to life. Try it at and

That dog in your photo? He's got something to say. 🐶 Turn your images into eight-second video clips with sound effects and speech in the Google Gemini and Flow from Google Labs. This feature uses Veo 3 to generate motion that reflects real world physics and includes a new experimental audio capability so you can really bring your images to life. Try it at and

Google AI

55,236 次观看 • 1 年前

Introducing WELLAIOS: A revolutionary Open source AI Agent development framework and launchpad on Solana WELLAIOS empowers you to create, tokenize, and trade advanced AI agents on the Solana blockchain. Built by our team of AI professionals, our platform combines a sophisticated open-source framework with multi-modal AI technology, bringing character creation and storytelling to life without having to write a single line of code. Create intelligent digital characters that evolve, interact, and generate content through our library of AI agents. Each character becomes a unique asset equipped with a large set of AI tools on the Solana blockchain. For developers and creators: Join our thriving ecosystem where innovation meets rewards. Build plugins, contribute to our open-source framework, and earn as your creations shape the future. 👀 Sneak Peek: Watch our 3D AI agent capabilities showcase for content creation. Coming soon to Solana. Follow us on X for exclusive updates and be part of the revolution.

Introducing WELLAIOS: A revolutionary Open source AI Agent development framework and launchpad on Solana WELLAIOS empowers you to create, tokenize, and trade advanced AI agents on the Solana blockchain. Built by our team of AI professionals, our platform combines a sophisticated open-source framework with multi-modal AI technology, bringing character creation and storytelling to life without having to write a single line of code. Create intelligent digital characters that evolve, interact, and generate content through our library of AI agents. Each character becomes a unique asset equipped with a large set of AI tools on the Solana blockchain. For developers and creators: Join our thriving ecosystem where innovation meets rewards. Build plugins, contribute to our open-source framework, and earn as your creations shape the future. 👀 Sneak Peek: Watch our 3D AI agent capabilities showcase for content creation. Coming soon to Solana. Follow us on X for exclusive updates and be part of the revolution.

WELL3

10,507 次观看 • 1 年前

Introducing Magic Orb🔮 Step into a new era of control with Magic Orb, an advanced tool that empowers alchemists to fine-tune AI generation settings to meet their specific needs. Designed for precision and adaptability, it allows unparalleled customization of outputs to ensure every creation aligns with your vision. Looking ahead, updates to the Multi-AI system will unlock granular control over individual AI configurations. Users will soon be able to manage and tweak multiple specialized AI entities within their applications, each optimized for a distinct function. Now, that’s Magic!🪄✨

Introducing Magic Orb🔮 Step into a new era of control with Magic Orb, an advanced tool that empowers alchemists to fine-tune AI generation settings to meet their specific needs. Designed for precision and adaptability, it allows unparalleled customization of outputs to ensure every creation aligns with your vision. Looking ahead, updates to the Multi-AI system will unlock granular control over individual AI configurations. Users will soon be able to manage and tweak multiple specialized AI entities within their applications, each optimized for a distinct function. Now, that’s Magic!🪄✨

ALCHEMIST AI 🔮

39,055 次观看 • 1 年前

$0 creator shoots are becoming the new ugc testing floor seedance 2.0 makes this “yapping” format way easier to scale not because every video has to look perfect because every video can feel like a different creator talking to the same buyer same script different face different hook different setting different tone different objection that’s how you turn one product into 40 creator-style tests without waiting on creators beauty angle fitness angle student angle founder angle customer rant angle problem-aware demo angle the winner isn’t always the best video it’s usually the one that feels most native to the buyer rt + comment "yapflow" and i’ll send you the seedance ai ugc workflow (follow for dm)

$0 creator shoots are becoming the new ugc testing floor seedance 2.0 makes this “yapping” format way easier to scale not because every video has to look perfect because every video can feel like a different creator talking to the same buyer same script different face different hook different setting different tone different objection that’s how you turn one product into 40 creator-style tests without waiting on creators beauty angle fitness angle student angle founder angle customer rant angle problem-aware demo angle the winner isn’t always the best video it’s usually the one that feels most native to the buyer rt + comment "yapflow" and i’ll send you the seedance ai ugc workflow (follow for dm)

Florin

10,363 次观看 • 2 个月前

Gemini Omni's motion control is f*cking cracked i just figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)

Gemini Omni's motion control is f*cking cracked i just figured out how to turn 1 reference video into 50+ AI videos with the exact same movements... you have a video of someone eating, dancing, using a product, doing whatever complex motion you need. you feed it to Gemini Omni and it recreates that exact motion with a completely new AI character in literally one prompt i've tested this against Kling motion control and it's not even close. Kling falls apart the moment you try anything complex. eating scenes look weird, hand movements get mangled, anything multi-step breaks down completely. Gemini Omni handles all of it if you're still using kling motion control or paying creators to split test your videos, this replaces that entire workflow here's the thing though. you can't just prompt this out of the box. if you try to do motion transfer with default prompting you're going to get errors or the motion won't transfer properly. there's a specific prompting method that makes it work every time so i packaged up the whole system.. here's what you're getting: > full step by step video breakdown > how to find the best reference videos to use > the exact prompting system that allows for motion control transfer so you never get errors > the workflow for batching this out at scale (1 video → 50+) RT + reply "MOTION" and i'll send it over (must follow so i can dm)

Miko

59,047 次观看 • 1 个月前

Today marks General Availability of AgentCore, a set of infrastructure building blocks for developers and companies to build secure, scalable agents. When we first started AWS, the vast majority of developers were spending most of their time on the undifferentiated heavy lifting of infrastructure instead of what differentiated their feature. So, we solved that problem by building primitive building blocks like compute and storage and database that would allow teammates and customers to quickly build and deploy new experiences without having to reinvent the wheel each time. We realized the same thing was happening with AI agents. It's too difficult and it's slowing customers down. That's why we created AgentCore, a set of services to build, deploy, and operate highly capable agents using any framework or model, with enterprise-grade security and scalability. These building blocks (like serverless secure runtime, memory, observability, a gateway that does MCP translation, etc) help customers tackle some of the biggest challenges of going from prototype to production, much more quickly, securely, and scalably. AgentCore has been in preview for several weeks, and customers have been quite excited about it. The AgentCore SDK has already been downloaded over a million times and we're seeing transformative results, such as Cohere Health expecting to reduce medical review times by 30-40% in highly regulated healthcare, and teams at Cox Automotive and Experian are embracing its flexibility to deploy and operate agents at scale. Inside Amazon, our Amazon Devices Operations & Supply Chain team is using AgentCore to develop an agentic manufacturing approach where AI agents work together to automate manual processes – turning what used to be days of engineering time into processes that take under an hour with high precision. Just like AWS changed how companies build and scale applications, we believe AgentCore will do the same for AI agents, enabling the next generation of innovation.

Today marks General Availability of AgentCore, a set of infrastructure building blocks for developers and companies to build secure, scalable agents. When we first started AWS, the vast majority of developers were spending most of their time on the undifferentiated heavy lifting of infrastructure instead of what differentiated their feature. So, we solved that problem by building primitive building blocks like compute and storage and database that would allow teammates and customers to quickly build and deploy new experiences without having to reinvent the wheel each time. We realized the same thing was happening with AI agents. It's too difficult and it's slowing customers down. That's why we created AgentCore, a set of services to build, deploy, and operate highly capable agents using any framework or model, with enterprise-grade security and scalability. These building blocks (like serverless secure runtime, memory, observability, a gateway that does MCP translation, etc) help customers tackle some of the biggest challenges of going from prototype to production, much more quickly, securely, and scalably. AgentCore has been in preview for several weeks, and customers have been quite excited about it. The AgentCore SDK has already been downloaded over a million times and we're seeing transformative results, such as Cohere Health expecting to reduce medical review times by 30-40% in highly regulated healthcare, and teams at Cox Automotive and Experian are embracing its flexibility to deploy and operate agents at scale. Inside Amazon, our Amazon Devices Operations & Supply Chain team is using AgentCore to develop an agentic manufacturing approach where AI agents work together to automate manual processes – turning what used to be days of engineering time into processes that take under an hour with high precision. Just like AWS changed how companies build and scale applications, we believe AgentCore will do the same for AI agents, enabling the next generation of innovation.

Andy Jassy

24,990 次观看 • 10 个月前

🚀Just launched: Amazon Q, the most capable GenAI-powered assistant is generally available today: Customers are using Q to transform how their teams get work done. When employees chat with Amazon Q, it provides immediate, relevant information and advice to help streamline tasks, speedup decision-making, and help spark creativity and innovation at work. . Early indications signal Amazon Q could help our customers’ employees become more than 80% more productive at their jobs; and with the new features we’re planning on introducing in the future, we think this will only continue to grow. 🟠 Amazon Q Developer allows developers to spend more time coding and less time on maintenance and performing other tedious, repetitive tasks. Q assists developers and IT professionals (IT pros) with all of their tasks—from coding, testing, and upgrading applications, to troubleshooting, performing security scanning and fixes, and optimizing AWS resources. Q also comes with Q Developer Agents which can autonomously perform range of tasks and we expect it to be the state of the art accuracy in benchmarks like SWE-Bench. 🟠 Amazon Q Business empowers employees to be more data-driven, and helps customers make better, faster decisions using company knowledge and data. Q Business is a generative AI–powered assistant that can answer questions, provide summaries, generate content, and securely complete tasks based on data and information in enterprise systems 🟠 Amazon Q Apps, a new and powerful capability of Amazon Q Business, enables employees to use natural language to quickly and securely build their own generative AI applications to automate daily tasks without requiring any prior coding experience. Employees simply describe the type of app they want, in natural language, and Q Apps will quickly generate an app that accomplishes their desired task, helping them streamline and automate their daily work with ease and efficiency.

🚀Just launched: Amazon Q, the most capable GenAI-powered assistant is generally available today: Customers are using Q to transform how their teams get work done. When employees chat with Amazon Q, it provides immediate, relevant information and advice to help streamline tasks, speedup decision-making, and help spark creativity and innovation at work. . Early indications signal Amazon Q could help our customers’ employees become more than 80% more productive at their jobs; and with the new features we’re planning on introducing in the future, we think this will only continue to grow. 🟠 Amazon Q Developer allows developers to spend more time coding and less time on maintenance and performing other tedious, repetitive tasks. Q assists developers and IT professionals (IT pros) with all of their tasks—from coding, testing, and upgrading applications, to troubleshooting, performing security scanning and fixes, and optimizing AWS resources. Q also comes with Q Developer Agents which can autonomously perform range of tasks and we expect it to be the state of the art accuracy in benchmarks like SWE-Bench. 🟠 Amazon Q Business empowers employees to be more data-driven, and helps customers make better, faster decisions using company knowledge and data. Q Business is a generative AI–powered assistant that can answer questions, provide summaries, generate content, and securely complete tasks based on data and information in enterprise systems 🟠 Amazon Q Apps, a new and powerful capability of Amazon Q Business, enables employees to use natural language to quickly and securely build their own generative AI applications to automate daily tasks without requiring any prior coding experience. Employees simply describe the type of app they want, in natural language, and Q Apps will quickly generate an app that accomplishes their desired task, helping them streamline and automate their daily work with ease and efficiency.

Swami Sivasubramanian

25,216 次观看 • 2 年前

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in

Making OpenCode as lean as Pi agent? Just trimmed 25k out of OpenCode's system prompt (from 30k to 4-5k tokens) How? Just disable skills and get rid of massive skill definition bloat. Who needs skills anyway? Just kidding, this is the not the way. It makes the agent lame and defeats the point of using one. But it sets a precedent: Find a way to use skills without their definitions pre-loaded into the system prompt every single turn. Another interesting stuff: Upon testing this temporary "no skill setup" with two of hottest OpenCode Zen free models, Mimo V2.5 vs DeepSeek V4 Flash: One thinks more and talks less One thinks less and talks more Check the video to see which is which If you made it here, I'm finding a way to leanest OpenCode setup that I can get I simply don't believe that OpenCode can't be as lean as Pi Upon tinkering, I made a plugin that temporarily extracts the system prompt while I test, and noticed the hundreds of definitions in it from my .agents/skills directory which is shared across all my coding agents (Cursor, Antigravity, Claude, etc.) Of course disabling skills is not the answer, but it just proved that there is a way to strip the system prompt of these massive skill defs Aside from the system prompt hierarchy that injects confusion imo if you have a conflicting and redundant AGENTS.md which I discovered upon digging into OpenCode's source code Apparently it has prompt.ts/system.ts/instruction.ts/llm.ts and loads base .txt prompts based on model family (claude/gpt-o/gpt-5/codex/gemini/others) that all work together to make OpenCode aware of who it was and how it should use tools and become a "coding agent" Gotta find the most minimal mix that fits right into my workflow Make OpenCode as lean as Pi? We'll see. All in

raymel 👋

37,478 次观看 • 2 个月前

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Fable 5 comes back！It can now build playable game prototypes. I think it is actually a signal for where AI coding is going. Making a game is not just “write some code.” Even a small browser game needs: game loop；character movement；collision logic；scoring system；UI states；physics tuning；visual feedback；bug fixing；playtesting This is why game prototyping is a great test for AI models. A model cannot fake it with a pretty answer. Either the game runs, or it does not. What impressed me about Fable 5 is that it is useful for the messy middle: turning an idea into mechanics, turning mechanics into code, debugging broken interactions, and iterating until the prototype feels playable. But here is the practical part: I would not use the strongest model for every step. For game building, I would split the workflow: 1. Fable 5 for game design + architecture 2. a fast coding model for routine implementation 3. a vision-capable model for screenshot/UI feedback 4. a cheaper model for docs, test cases, and small fixes 5. fallback when latency, cost, or output quality becomes a problem That is the real AI coding stack. Not “one magic model does everything.” More like: the right model, for the right task, at the right cost, with fallback when things break. This is why I’ve been looking at ZenMux ZenMux. ZenMux gives developers one gateway to access multiple leading AI models, with OpenAI / Anthropic / Google Vertex compatible APIs, cost tracking, quality benchmarks, auto-routing, and compensation when output quality, latency, or throughput falls short. If AI can now make games, the next question is not just “which model is strongest?” It is:how do we manage the whole model workflow Fable 5 shows the creative ceiling. ZenMux is closer to the infrastructure layer you need when AI coding becomes a real production habit.

Rachel🥥

61,143 次观看 • 1 个月前

We’re solving problems that aren’t problems in America This is the new automated ketchup dispenser from Server Products at Raising Canes I think there is a bigger plan with these new dispensers, and they’re being rolled out at multiple chains. These dispensers are IoT-enabled in newer models, meaning they can monitoring usage and inventory This kind of tracking and quickly turn into new features like restricting the amount of condiments one user can get, similar to what’s being done with soda machines and QR codes It starts as convenience, and ends with restrictions and control

We’re solving problems that aren’t problems in America This is the new automated ketchup dispenser from Server Products at Raising Canes I think there is a bigger plan with these new dispensers, and they’re being rolled out at multiple chains. These dispensers are IoT-enabled in newer models, meaning they can monitoring usage and inventory This kind of tracking and quickly turn into new features like restricting the amount of condiments one user can get, similar to what’s being done with soda machines and QR codes It starts as convenience, and ends with restrictions and control

Wall Street Apes

944,054 次观看 • 2 个月前

Today we’re introducing Google AI Threat Defense - a comprehensive AI-powered cybersecurity solution designed to help continuously monitor for and stop AI-powered threats before they can impact your business. Here’s how it works: 1. AI Threat Defense uses our cybersecurity platform Wiz to scan and prioritize what applications and systems have the highest security risk. 2. Gemini and other frontier AI models can then autonomously perform continual deep scanning of your applications - starting with those at the highest risk - to identify security vulnerabilities. 3. The capabilities of CodeMender - a new software repair agent - are then used to verify and accelerate the patching of vulnerabilities. 4. And our Wiz autonomous agents continuously test your systems to find unknown vulnerabilities before adversaries do so that you can remediate them before you are attacked. While other model providers focus on using AI to find and flag vulnerabilities, Google AI Threat Defense actively prioritizes your most critical real-world risks and accelerates their remediation using a variety of models since no single model finds a superset of the vulnerabilities found by all other models.

Today we’re introducing Google AI Threat Defense - a comprehensive AI-powered cybersecurity solution designed to help continuously monitor for and stop AI-powered threats before they can impact your business. Here’s how it works: 1. AI Threat Defense uses our cybersecurity platform Wiz to scan and prioritize what applications and systems have the highest security risk. 2. Gemini and other frontier AI models can then autonomously perform continual deep scanning of your applications - starting with those at the highest risk - to identify security vulnerabilities. 3. The capabilities of CodeMender - a new software repair agent - are then used to verify and accelerate the patching of vulnerabilities. 4. And our Wiz autonomous agents continuously test your systems to find unknown vulnerabilities before adversaries do so that you can remediate them before you are attacked. While other model providers focus on using AI to find and flag vulnerabilities, Google AI Threat Defense actively prioritizes your most critical real-world risks and accelerates their remediation using a variety of models since no single model finds a superset of the vulnerabilities found by all other models.

Thomas Kurian

197,739 次观看 • 2 个月前

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Karpathy's Agentic Engineering finally has proper tooling! (built by Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.

Akshay 🚀

257,420 次观看 • 1 个月前

⚡️INTRODUCING HARDSTAKE, BOOSTS AND SAFE LP TRANSFERS This very important update concerns creators, users, liquidity providers and integrators. Please read carefully and hang tight HARDSTAKE: A new router function that allows projects to implement any custom staking logic safely on any ERC20, adhering to the Ethervista Euler model. This opens up new possibilities for token economics, including locking LP tokens permanently while still earning rewards - effectively "burning" tokens without losing benefits. The $VISTA token will be the first to implement HARDSTAKE 👇 Ethervista will now offer BOOSTS, allowing new projects to advertise directly on for an ETH fee. This feature gives launched tokens instant exposure to our large user base. All BOOST fees go straight to $VISTA stakers. It's our way of ensuring supporters benefit directly from ETHERVISTA's growth. This system exemplifies our core idea: traders, creators, and providers working together to create value for everyone involved. To ensure a smooth rollout of these new features, we're implementing a phased approach: 1. One-week integration period: We're giving everyone time to adapt to these changes and build accordingly before deploying to mainnet. 2. Public audit: During this week, we're opening a public audit period. Any bugs found will be generously rewarded 3. Documentation: Comprehensive documentation is available at providing detailed information on HARDSTAKE and safe LP transfers. 4. Developer support: We've opened a dedicated developer chat on Discord to offer full support and answer any questions during the integration process.

⚡️INTRODUCING HARDSTAKE, BOOSTS AND SAFE LP TRANSFERS This very important update concerns creators, users, liquidity providers and integrators. Please read carefully and hang tight HARDSTAKE: A new router function that allows projects to implement any custom staking logic safely on any ERC20, adhering to the Ethervista Euler model. This opens up new possibilities for token economics, including locking LP tokens permanently while still earning rewards - effectively "burning" tokens without losing benefits. The $VISTA token will be the first to implement HARDSTAKE 👇 Ethervista will now offer BOOSTS, allowing new projects to advertise directly on for an ETH fee. This feature gives launched tokens instant exposure to our large user base. All BOOST fees go straight to $VISTA stakers. It's our way of ensuring supporters benefit directly from ETHERVISTA's growth. This system exemplifies our core idea: traders, creators, and providers working together to create value for everyone involved. To ensure a smooth rollout of these new features, we're implementing a phased approach: 1. One-week integration period: We're giving everyone time to adapt to these changes and build accordingly before deploying to mainnet. 2. Public audit: During this week, we're opening a public audit period. Any bugs found will be generously rewarded 3. Documentation: Comprehensive documentation is available at providing detailed information on HARDSTAKE and safe LP transfers. 4. Developer support: We've opened a dedicated developer chat on Discord to offer full support and answer any questions during the integration process.

Ethervista

40,145 次观看 • 1 年前