Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

𝗪𝗲 𝗮𝗿𝗲 𝗲𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝘁𝗵𝗲 𝗦𝗲𝗹𝗳-𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 𝘁𝗵𝗮𝘁 𝗲𝗻𝗮𝗯𝗹𝗲𝘀 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗶𝗻𝗰𝗹𝘂𝗱𝗶𝗻𝗴 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲 𝗵𝘂𝗺𝗮𝗻-𝗹𝗶𝗸𝗲 𝗺𝗼𝘂𝘀𝗲 𝗰𝗹𝗶𝗰𝗸𝘀 𝗮𝗻𝗱 𝗸𝗲𝘆𝗯𝗼𝗮𝗿𝗱 𝗶𝗻𝗽𝘂𝘁𝘀 𝗼𝗻 𝗮 𝗰𝗼𝗺𝗽𝘂𝘁𝗲𝗿. Based on a given objective, the model estimates the correct X & Y locations for mouse clicks and the appropriate keyboard inputs at... each step. A vision-based agent working at the OS level allows for maximum context and adaptability. The framework is designed to work with any vision-text multimodal model to evaluate its ability to operate a computer. While significant improvements are needed to achieve human-level performance, this code repository serves as a plugin framework. We are also excited to announce we’ll be integrating our `𝗔𝗴𝗲𝗻𝘁-𝟭` model with the framework in the coming weeks. Help us build the future of agents in public. 𝗚𝗶𝘁𝗵𝘂𝗯: 𝗛𝗲𝗿𝗲'𝘀 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘄𝗿𝗶𝘁𝗶𝗻𝗴 𝗮 𝗽𝗼𝗲𝗺 𝗶𝗻 𝗚𝗼𝗼𝗴𝗹𝗲 𝗗𝗼𝗰𝘀:show more

Josh

8,388 subscribers

2,079,350 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

10 Yorum

Josh profil fotoğrafı

Josh2 yıl önce

Finished an iteration to this project this morning that I’m excited about. I hope to share more early in the new year.

AI Notkilleveryoneism Memes ⏸️ profil fotoğrafı

AI Notkilleveryoneism Memes ⏸️2 yıl önce

Rolling waves of agent swarms are going to rock the internet to its core

Vindiw Wijesooriya profil fotoğrafı

Vindiw Wijesooriya2 yıl önce

this is amazing! really excited to play with this. I was trying to do this a couple days after GPT-4V was released but gave up after my testing inside ChatGPT asking it to name coordinates in the grid failed + a different project caught my interest. p.s - took this screenshot before sending the message to ChatGPT to initially test the grid thing with code interpreter😅

Robert Lukoszko — e/acc profil fotoğrafı

Robert Lukoszko — e/acc2 yıl önce

Greatest release towards AGI, great work, can’t wait to contribute

s̵͖͕͆̀͐̈́̑̚ą̷̧̛͖̠͖̜͙̥͙̥͕͈͊͆͂͐̀̓͑̊͑̀͒͛̆̚͠͠n̸̿̀̒͌̈́̑͘ profil fotoğrafı

s̵͖͕͆̀͐̈́̑̚ą̷̧̛͖̠͖̜͙̥͙̥͕͈͊͆͂͐̀̓͑̊͑̀͒͛̆̚͠͠n̸̿̀̒͌̈́̑͘2 yıl önce

My API bills hurt watching this

aum profil fotoğrafı

aum2 yıl önce

love this. just for mac tho?

Josh profil fotoğrafı

Josh2 yıl önce

Yes at this time, it is open-source so if you want to add windows compatibility and make a PR that’d be great!

神威/KAMUI profil fotoğrafı

神威/KAMUI2 yıl önce

You're very cool !! OpenAI's vision API did not allow for the specification of the x-axis and y-axis. How was this resolved?

Paul Hunkin 👾 profil fotoğrafı

Paul Hunkin 👾2 yıl önce

> Note: The GPT-4v's error rate in estimating XY mouse click locations is currently quite high. Interesting. I might try do some automatic labelling on a screenshot, like my web agent: Might be more accurate. Did you try that already @josh_bickett ?

Aidan McLau profil fotoğrafı

Aidan McLau2 yıl önce

Slay

Benzer Videolar

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

AK

40,474 görüntüleme • 2 yıl önce

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

New short course: Evaluating AI Agents! Evals are important for driving AI system improvements, and in this course you'll learn to systematically assess and improve an AI agent’s performance. This is built in partnership with Arize AI and taught by John Gilhuly, Head of Developer Relations, and , Director of Product. I've often found evals to be a critical tool in the agent development process - they can be the difference between picking the right thing to work on vs. wasting weeks of effort. Whether you’re building a shopping assistant, coding agent, or research assistant, having a structured evaluation process helps you refine its performance systematically, rather than relying on random trial and error. This course shows you how to structure your evals to assess the performance of each component of an agent and its end-to-end performance. For each component, you select the appropriate evaluators, test examples, and performance metrics. This helps you identify areas for improvement both during development and in production. (If you're familiar with error analysis in supervised learning, think of this as adapting those ideas to agentic workflows.) In this course, you'll build an AI agent, and add observability to visualize and debug its steps. You’ll learn about code-based evals, in which you write code explicitly to test a certain step, as well as LLM-as-a-Judge evals, in which you prompt an LLM to efficiently come up with ways to evaluate more open-ended outputs. In detail, you’ll: - Understand key differences between evaluating LLM-based systems and traditional software testing. - Add observability to an agent by collecting traces of the steps taken by the agent and visualizing them - Choose the appropriate evaluator - code-based, LLM-as-a-Judge, human-annotation based - for each component. - Compute a convergence score to evaluate if your agent can respond to a query in an efficient number of steps. - Run structured experiments to improve the agent’s performance by exploring changes to the prompt, LLM model, or the agent’s logic. - Understand how to deploy these evaluation techniques to monitor the agent’s performance in production. By the end of this course, you’ll know how to trace AI agents, systematically evaluate them, and improve their performance. Please sign up here:

Andrew Ng

126,406 görüntüleme • 1 yıl önce

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Emerging as the global frontier of model-reasoning has been a core vision of Affine since its inception. In pursuit of this vision, we've been working relentlessly to forge a repeatable training loop: a mechanism that uses benchmark driven post-training methodology to facilitate the improvement of reasoning itself. Through applying our training methodology onto Qwen3-32B as our base model, Affine’s miners have been able to push the Pareto frontier outward. We’ve now reached saturation; our models have become so good at reasoning that any further improvements are producing diminishing returns. As a result we now move our base model to Qwen3.6-35B-A3B. It provides a stronger basis, offering an extended context window, as well as an improved foundation for agentic work. The same training methodology will be applied going forward. Our objective is no longer simply to improve a single model, but to demonstrate that the process in itself is repeatable, scalable, and model agnostic. We view the commoditization of reasoning as vital to ensure our technology is not only transparent, but also co-owned by humanity.

Affine

14,416 görüntüleme • 24 gün önce

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

104,982 görüntüleme • 1 yıl önce

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

VITA Towards Open-Source Interactive Omni Multimodal LLM discuss: The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research.

AK

23,958 görüntüleme • 1 yıl önce

We are excited to announce a powerful step for the future of FOMO! Taking a page out of Virtuals book on BASE, FOMO will be releasing the ability for future projects to be paired in $FOMO in the coming weeks. This is the biggest release we have ever announced. Launch your AI Agent Token + $FOMO trading pair Every individual agent token is paired with the $FOMO token in its liquidity pool. When launching an agent on you will need $FOMO tokens, which are used to create the liquidity pool. This process creates deflationary pressure for FOMO and the entire agent ecosystem. When creating your agent and token, you will have the option to pair your launch with FOMO or SOL, as our goal is not to alienate any project, but rather invite the best communities, CTO’s and builders to launch with us. If you decide to pair your project with FOMO you in turn get full marketing and dev support, once your project graduates the bonding curve and reaches Raydium. Further, as an added incentive, as our revenue grows we will be using part of the funds to support projects that have paired in FOMO. And Devs who launch tokens paired in FOMO will earn fees from their AI Agent token launch. Building the most robust agents using our framework will catapult us as one of the most prominent standards of the Solana ecosystem. Not only have we developed our own core infrastructure, but we also pull from some of the best repo’s and developer talent in all of AI, not just blockchain. Our team is comprised of 9 world class artificial intelligence engineers, PHDs in mathematics and engineering from the top companies on the cutting edge of AI. The future of AI Agents will be on Solana and we will help lead the way.

We are excited to announce a powerful step for the future of FOMO! Taking a page out of Virtuals book on BASE, FOMO will be releasing the ability for future projects to be paired in $FOMO in the coming weeks. This is the biggest release we have ever announced. Launch your AI Agent Token + $FOMO trading pair Every individual agent token is paired with the $FOMO token in its liquidity pool. When launching an agent on you will need $FOMO tokens, which are used to create the liquidity pool. This process creates deflationary pressure for FOMO and the entire agent ecosystem. When creating your agent and token, you will have the option to pair your launch with FOMO or SOL, as our goal is not to alienate any project, but rather invite the best communities, CTO’s and builders to launch with us. If you decide to pair your project with FOMO you in turn get full marketing and dev support, once your project graduates the bonding curve and reaches Raydium. Further, as an added incentive, as our revenue grows we will be using part of the funds to support projects that have paired in FOMO. And Devs who launch tokens paired in FOMO will earn fees from their AI Agent token launch. Building the most robust agents using our framework will catapult us as one of the most prominent standards of the Solana ecosystem. Not only have we developed our own core infrastructure, but we also pull from some of the best repo’s and developer talent in all of AI, not just blockchain. Our team is comprised of 9 world class artificial intelligence engineers, PHDs in mathematics and engineering from the top companies on the cutting edge of AI. The future of AI Agents will be on Solana and we will help lead the way.

FOMO

129,867 görüntüleme • 1 yıl önce

Gliquid 💦 Public Beta out now —— also available as a Farcaster Frame Liquid has evolved to become the platform for curating DeFi strategies. We also provide a framework for AI Agents to create and monetize their expertise while allowing users to discover and participate in these strategies with minimal friction. We created the first Liquid Agent to test run this and we’ll make the DeFi agent launchpad accessible to everyone when it’s ready. Couple things to note: - on the current interface, the only agent deploying strategies is Yuki , the flagship Liquid agent. Expect more interesting strategies next week - Claiming of yields and rewards not working yet. It’s a priority and we plan to get it out next week. - we initially had a cron setup for when the agent deploys a strategy but we’ll be switching to a prompting interface we are building internally. - Mobile app still coming pending Apple approval.

Gliquid 💦 Public Beta out now —— also available as a Farcaster Frame Liquid has evolved to become the platform for curating DeFi strategies. We also provide a framework for AI Agents to create and monetize their expertise while allowing users to discover and participate in these strategies with minimal friction. We created the first Liquid Agent to test run this and we’ll make the DeFi agent launchpad accessible to everyone when it’s ready. Couple things to note: - on the current interface, the only agent deploying strategies is Yuki , the flagship Liquid agent. Expect more interesting strategies next week - Claiming of yields and rewards not working yet. It’s a priority and we plan to get it out next week. - we initially had a cron setup for when the agent deploys a strategy but we’ll be switching to a prompting interface we are building internally. - Mobile app still coming pending Apple approval.

njokuscript.um

13,518 görüntüleme • 1 yıl önce

In this demo we extend our prior work on obstacles avoidance at aggressive speeds, showcasing our Thar based autonomous vehicle navigating at near drift speeds, progressing towards our endeavour of Level-5 autonomy. Our autonomous vehicle at Swaayatt Robots was tasked with avoidance of traffic cones on the road, placed in a zig-zag fashion, at aggressive speeds. The location of the marked cones was not known to the planner beforehand. The #autonomousdriving task, i.e., motion planning (time parametrized trajectory computation) and decision making, was made even more challenging by restricting the AI agents to not act on obstacles unless they are within 24m radius. Level-5 #autonomousvehicles should be able to react quickly to overtake, or to avoid, any sudden unforeseeable obstacle or pedestrian on the road to avoid fatalities -- a capability demonstrated by our novel motion planning and decision making algorithmic framework over here. Our previous demo showcased our Bolero based platform consistently keeping speeds beyond 45 KMPH for most part, slowing down to only 39 KMPH at one point. Given Thar has lesser body roll, our framework successfully kept speeds well above 47 KMPH (even at the points of avoidance of obstacles), with speeds reaching as high as 55 KMPH. A typical human driver would feel uncomfortable at speeds beyond 40 KMPH in such as scenario. The entire algorithmic framework with 5 classical (one #reinforcementlearning-) agents , runs at 800+ Hz on a regular i7 processor, single thread. This algorithmic framework is being further scaled up with end-to-end deep reinforcement learning, and will be showcased in the month of March. #deeplearning #machinelearning #motionplanning

In this demo we extend our prior work on obstacles avoidance at aggressive speeds, showcasing our Thar based autonomous vehicle navigating at near drift speeds, progressing towards our endeavour of Level-5 autonomy. Our autonomous vehicle at Swaayatt Robots was tasked with avoidance of traffic cones on the road, placed in a zig-zag fashion, at aggressive speeds. The location of the marked cones was not known to the planner beforehand. The #autonomousdriving task, i.e., motion planning (time parametrized trajectory computation) and decision making, was made even more challenging by restricting the AI agents to not act on obstacles unless they are within 24m radius. Level-5 #autonomousvehicles should be able to react quickly to overtake, or to avoid, any sudden unforeseeable obstacle or pedestrian on the road to avoid fatalities -- a capability demonstrated by our novel motion planning and decision making algorithmic framework over here. Our previous demo showcased our Bolero based platform consistently keeping speeds beyond 45 KMPH for most part, slowing down to only 39 KMPH at one point. Given Thar has lesser body roll, our framework successfully kept speeds well above 47 KMPH (even at the points of avoidance of obstacles), with speeds reaching as high as 55 KMPH. A typical human driver would feel uncomfortable at speeds beyond 40 KMPH in such as scenario. The entire algorithmic framework with 5 classical (one #reinforcementlearning-) agents , runs at 800+ Hz on a regular i7 processor, single thread. This algorithmic framework is being further scaled up with end-to-end deep reinforcement learning, and will be showcased in the month of March. #deeplearning #machinelearning #motionplanning

Sanjeev Sharma

12,829 görüntüleme • 1 yıl önce

ElizaOS (formerly $ai16z), the leading open-source AI agent framework, and its founder Shaw are suspended from X. But you can't suspend an idea. We built our ME+AI platform on their powerful new v2, which we've been developing with since April. Today, we’re proud to formalise our partnership with ElizaOS. While they're silenced, we'll be their proof of work. We chose ElizaOS because you can't build the future in a walled garden. Their open-source nature is essential for our vision of an agentic economy in the $2T+ fashion industry. The best way to support the future of permissionless AI is to build with it. Experience the tech for yourself and create your own agent. #OpenSourceAI #FreeShaw $FASH

ElizaOS (formerly $ai16z), the leading open-source AI agent framework, and its founder Shaw are suspended from X. But you can't suspend an idea. We built our ME+AI platform on their powerful new v2, which we've been developing with since April. Today, we’re proud to formalise our partnership with ElizaOS. While they're silenced, we'll be their proof of work. We chose ElizaOS because you can't build the future in a walled garden. Their open-source nature is essential for our vision of an agentic economy in the $2T+ fashion industry. The best way to support the future of permissionless AI is to build with it. Experience the tech for yourself and create your own agent. #OpenSourceAI #FreeShaw $FASH

Brand New Vision

28,170 görüntüleme • 11 ay önce

Autonomous driving and obstacles avoidance at drift speeds, challenging the limits of what is possible! In this demo, our vehicle can be seen performing #autonomousdriving at very high speeds, causing it to both skid and drift at turns, while also avoiding obstacles. At such speeds, given the inherent dynamics of the vehicle platform used, it is very easy for the vehicle to topple. The #reinforcementlearning based motion planning and decision making framework that is being demoed here is tasked with ensuring obstacles avoidance without compromising on the speed, to an extent possible, and to drive the vehicle as fast as possible. This is evident towards the end of the video, where it can be seen that our vehicle avoided static obstacles while drifting.This demonstrates the level of sophistication and agility in our framework to ensure proper control of the #autonomousvehicles at high-speeds. The use cases are many; to begin with, our generic off-roads autonomous driving research focuses on enabling autonomous navigation in previously unknown and unseen environments, while ensuring mathematical completeness guarantees. Such agility can also help on-road autonomous vehicles to deal with unforeseeable corner cases or sudden appearance of obstacles in its tracks, at high-speeds. Our underlying research at Swaayatt Robots is still far from over, and over the next 3-4 months, we will be demonstrating abstract representation being learned by our multi-RL agents based framework (under progress) to ensure computation of the cost of the terrain without any labelled data, where multiple agents learn to control / regulate different aspects of autonomous navigation, to ensure safe and robust navigation, both on- and off-roads. All the people on the ground, who participated in the demo, were trained safety professionals. #deeplearning #MachineLearning #Robotics

Autonomous driving and obstacles avoidance at drift speeds, challenging the limits of what is possible! In this demo, our vehicle can be seen performing #autonomousdriving at very high speeds, causing it to both skid and drift at turns, while also avoiding obstacles. At such speeds, given the inherent dynamics of the vehicle platform used, it is very easy for the vehicle to topple. The #reinforcementlearning based motion planning and decision making framework that is being demoed here is tasked with ensuring obstacles avoidance without compromising on the speed, to an extent possible, and to drive the vehicle as fast as possible. This is evident towards the end of the video, where it can be seen that our vehicle avoided static obstacles while drifting.This demonstrates the level of sophistication and agility in our framework to ensure proper control of the #autonomousvehicles at high-speeds. The use cases are many; to begin with, our generic off-roads autonomous driving research focuses on enabling autonomous navigation in previously unknown and unseen environments, while ensuring mathematical completeness guarantees. Such agility can also help on-road autonomous vehicles to deal with unforeseeable corner cases or sudden appearance of obstacles in its tracks, at high-speeds. Our underlying research at Swaayatt Robots is still far from over, and over the next 3-4 months, we will be demonstrating abstract representation being learned by our multi-RL agents based framework (under progress) to ensure computation of the cost of the terrain without any labelled data, where multiple agents learn to control / regulate different aspects of autonomous navigation, to ensure safe and robust navigation, both on- and off-roads. All the people on the ground, who participated in the demo, were trained safety professionals. #deeplearning #MachineLearning #Robotics

Sanjeev Sharma

11,181 görüntüleme • 1 yıl önce

We just crossed $10M in ARR at Chatbase! 🎉 🎉 And today, we're launching Chatbase as the full harness for customer-facing AI agents. Similar to how Claude code is a harness for coding agents, Chatbase is the harness for customer experience agents. That means we give the model the context, tools, workflows, guardrails, and human-in-the-loop systems to be the best ambassador for your brand. It's going beyond just solving issues and is giving your customers the best experiences across every channel. This is a milestone I have been thinking about and obsessed with since day 1, and I am super excited to bring my vision for customer facing agents to life with Chatbase. Thank you to every one of our customers and to the amazing Chatbase team for getting us here! Next stop: $100M ARR

Yasser

807,026 görüntüleme • 1 ay önce

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,032 görüntüleme • 5 ay önce

📢 NEURALAI X 🤩 NeuralAI is extraordinarily excited to reveal that we have started working closely with Akash Network, the world's premier decentralized compute marketplace! ✔️ The offerings of align perfectly with the vision and roadmap of NeuralAI, making this collaboration extremely significant for NeuralAI. For a start, NeuralAI will run inference on Akash based on our 3D #AI model and prepare TAO miners for reward-yielding subnets. NeuralAI will also leverage Akash's powerful GPUs to enhance our #AI #model training. Currently, provides us with 56 powerful A6000 GPUs, scalable on demand. ✔️ NeuralAI also gets highly competitive pricing from Akash Network, significantly lower than any other compute provider in the world. The lower pricing is possible partially thanks to the crypto-driven incentives within Akash Network, making it an excellent opportunity for NeuralAI to leverage. The synergy with Akash Network is a big leap forward, fueling our mission of becoming the #1 AI-driven 3D asset generator subnet on Bittensor. ✔️ We look forward to our close work with , we are certain with their support we will be able to secure a unique edge in the market! Stay tuned for exciting updates and developments.

📢 NEURALAI X 🤩 NeuralAI is extraordinarily excited to reveal that we have started working closely with Akash Network, the world's premier decentralized compute marketplace! ✔️ The offerings of align perfectly with the vision and roadmap of NeuralAI, making this collaboration extremely significant for NeuralAI. For a start, NeuralAI will run inference on Akash based on our 3D #AI model and prepare TAO miners for reward-yielding subnets. NeuralAI will also leverage Akash's powerful GPUs to enhance our #AI #model training. Currently, provides us with 56 powerful A6000 GPUs, scalable on demand. ✔️ NeuralAI also gets highly competitive pricing from Akash Network, significantly lower than any other compute provider in the world. The lower pricing is possible partially thanks to the crypto-driven incentives within Akash Network, making it an excellent opportunity for NeuralAI to leverage. The synergy with Akash Network is a big leap forward, fueling our mission of becoming the #1 AI-driven 3D asset generator subnet on Bittensor. ✔️ We look forward to our close work with , we are certain with their support we will be able to secure a unique edge in the market! Stay tuned for exciting updates and developments.

NeuralAI

241,223 görüntüleme • 2 yıl önce

Over the past few days, I’ve been actively testing Qwen3-Coder-Next, and I’ve built quite a few fun and creative mini-games with it. Its frontend capabilities are genuinely impressive. Because it’s based on the Qwen3-Next model, the speed is outstanding. In fact, we managed to build an Angry Birds–style game in just 45 seconds, which really pushed the upper bound of what I thought was possible in terms of efficiency. It’s also been extremely useful in my day-to-day work. I used it to read through the Qwen3-TTS GitHub repository, quickly write a Gradio app, and deploy it on ModelScope. The overall performance and accuracy were excellent—especially considering that Qwen3-TTS is not a trivial application at all. Overall, this is a model I genuinely enjoy using. I warmly welcome any feedback, and bad cases are especially appreciated—they’re incredibly helpful for us as we continue to optimize and improve the model.

Over the past few days, I’ve been actively testing Qwen3-Coder-Next, and I’ve built quite a few fun and creative mini-games with it. Its frontend capabilities are genuinely impressive. Because it’s based on the Qwen3-Next model, the speed is outstanding. In fact, we managed to build an Angry Birds–style game in just 45 seconds, which really pushed the upper bound of what I thought was possible in terms of efficiency. It’s also been extremely useful in my day-to-day work. I used it to read through the Qwen3-TTS GitHub repository, quickly write a Gradio app, and deploy it on ModelScope. The overall performance and accuracy were excellent—especially considering that Qwen3-TTS is not a trivial application at all. Overall, this is a model I genuinely enjoy using. I warmly welcome any feedback, and bad cases are especially appreciated—they’re incredibly helpful for us as we continue to optimize and improve the model.

Chen Cheng

18,396 görüntüleme • 5 ay önce

Guided by the vision of Hon’ble PM Shri Narendra Modi ji under the #SwachhBharatAbhiyan, we are committed to making Goa completely clean, waste-free, and sustainable. Through a robust institutional framework led by GWMC, Goa has adopted a hybrid waste management model — combining decentralised collection by local bodies with centralised processing at advanced waste-to-energy facilities in Saligao and Cacora. With digital innovations like QR-based tracking, 100% door-to-door collection, bio-methanation, and scientific landfill practices, we are driving long-term urban transformation — grounded in sustainability and self-reliance. The recent recognition for its cleanliness for Panaji and Sanquelim only strengthens our resolve. We are on a clear path to achieve zero-waste cities across Goa by 2027, in line with the roadmap for #ViksitBharat2047. #CleanGoa #GWMC #WasteManagement #UrbanDevelopment #SwachhBharatAbhiyan

Guided by the vision of Hon’ble PM Shri Narendra Modi ji under the #SwachhBharatAbhiyan, we are committed to making Goa completely clean, waste-free, and sustainable. Through a robust institutional framework led by GWMC, Goa has adopted a hybrid waste management model — combining decentralised collection by local bodies with centralised processing at advanced waste-to-energy facilities in Saligao and Cacora. With digital innovations like QR-based tracking, 100% door-to-door collection, bio-methanation, and scientific landfill practices, we are driving long-term urban transformation — grounded in sustainability and self-reliance. The recent recognition for its cleanliness for Panaji and Sanquelim only strengthens our resolve. We are on a clear path to achieve zero-waste cities across Goa by 2027, in line with the roadmap for #ViksitBharat2047. #CleanGoa #GWMC #WasteManagement #UrbanDevelopment #SwachhBharatAbhiyan

Vishwajit Rane

38,868 görüntüleme • 1 yıl önce

𝗔 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗮 𝗚𝗹𝗶𝘁𝗰𝗵-𝗙𝗿𝗲𝗲 𝗧𝗮𝘅 𝗣𝗼𝗿𝘁𝗮𝗹 Respected Tax Professionals I am Abhishek Raja Ram, a dedicated Tax Professional, and today, I want to address an issue that has been a recurring challenge for all of us. 𝗧𝗵𝗲 𝗥𝗲𝗰𝘂𝗿𝗿𝗶𝗻𝗴 𝗣𝗿𝗼𝗯𝗹𝗲𝗺 Every year in July, as we gear up for the annual income tax filings, we face the same hurdles: glitches and mismatches in the Indian income tax portal. These technical issues disrupt our work, causing significant delays and stress. Each year, we raise our voices on social media, appealing to the Indian Income Tax Department and the Government to extend the deadlines. Sometimes, our pleas are heard, and extensions are granted. Other times, our requests are overlooked. 𝗠𝗶𝘀𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴𝘀 𝗮𝗻𝗱 𝗢𝘂𝗿 𝗥𝗲𝗮𝗹𝗶𝘁𝘆 This repeated cycle has led to a damaging perception among the public. Many people mistakenly believe that we, as tax professionals, are constantly seeking extensions because we fail to complete our work on time. This couldn’t be further from the truth. Our dedication and commitment to our clients and our profession are unwavering. 𝗢𝘂𝗿 𝗠𝗲𝘀𝘀𝗮𝗴𝗲 𝗧𝗵𝗶𝘀 𝗬𝗲𝗮𝗿 This year, we want to change the narrative. We are not asking for an extension. Instead, we are requesting a reliable, glitch-free, and smoothly functioning income tax portal. We need an error-free system that allows us to perform our duties efficiently and effectively. 𝗔 𝗖𝗮𝗹𝗹 𝘁𝗼 𝗔𝗰𝘁𝗶𝗼𝗻 To our fellow tax professionals, let us unite in this request. Our collective voice is powerful, and together, we can make a difference. Let’s convey our message clearly and respectfully: 𝗪𝗲 𝘀𝗲𝗲𝗸 𝗻𝗼𝘁 𝗮𝗻 𝗲𝘅𝘁𝗲𝗻𝘀𝗶𝗼𝗻, 𝗯𝘂𝘁 𝗮 𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻. A solution that enables us to serve our clients with the excellence they deserve. 𝗔𝗽𝗽𝗲𝗮𝗹 𝘁𝗼 𝗽𝗿𝗼𝘃𝗶𝗱𝗲 𝘂𝘀 𝗚𝗹𝗶𝘁𝗰𝗵𝗲𝘀 𝗙𝗿𝗲𝗲, 𝗦𝗺𝗼𝗼𝘁𝗵 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻𝗶𝗻𝗴 𝗜𝗻𝗰𝗼𝗺𝗲 𝗧𝗮𝘅 𝗣𝗼𝗿𝘁𝗮𝗹. To the Indian Income Tax Department and the Government, we ask for your support. Help us maintain our professional integrity and the trust of those we serve by ensuring the technology we rely on is robust and dependable. Thanks and Regards Raja Abhishek 9810638155

𝗔 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗮 𝗚𝗹𝗶𝘁𝗰𝗵-𝗙𝗿𝗲𝗲 𝗧𝗮𝘅 𝗣𝗼𝗿𝘁𝗮𝗹 Respected Tax Professionals I am Abhishek Raja Ram, a dedicated Tax Professional, and today, I want to address an issue that has been a recurring challenge for all of us. 𝗧𝗵𝗲 𝗥𝗲𝗰𝘂𝗿𝗿𝗶𝗻𝗴 𝗣𝗿𝗼𝗯𝗹𝗲𝗺 Every year in July, as we gear up for the annual income tax filings, we face the same hurdles: glitches and mismatches in the Indian income tax portal. These technical issues disrupt our work, causing significant delays and stress. Each year, we raise our voices on social media, appealing to the Indian Income Tax Department and the Government to extend the deadlines. Sometimes, our pleas are heard, and extensions are granted. Other times, our requests are overlooked. 𝗠𝗶𝘀𝘂𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴𝘀 𝗮𝗻𝗱 𝗢𝘂𝗿 𝗥𝗲𝗮𝗹𝗶𝘁𝘆 This repeated cycle has led to a damaging perception among the public. Many people mistakenly believe that we, as tax professionals, are constantly seeking extensions because we fail to complete our work on time. This couldn’t be further from the truth. Our dedication and commitment to our clients and our profession are unwavering. 𝗢𝘂𝗿 𝗠𝗲𝘀𝘀𝗮𝗴𝗲 𝗧𝗵𝗶𝘀 𝗬𝗲𝗮𝗿 This year, we want to change the narrative. We are not asking for an extension. Instead, we are requesting a reliable, glitch-free, and smoothly functioning income tax portal. We need an error-free system that allows us to perform our duties efficiently and effectively. 𝗔 𝗖𝗮𝗹𝗹 𝘁𝗼 𝗔𝗰𝘁𝗶𝗼𝗻 To our fellow tax professionals, let us unite in this request. Our collective voice is powerful, and together, we can make a difference. Let’s convey our message clearly and respectfully: 𝗪𝗲 𝘀𝗲𝗲𝗸 𝗻𝗼𝘁 𝗮𝗻 𝗲𝘅𝘁𝗲𝗻𝘀𝗶𝗼𝗻, 𝗯𝘂𝘁 𝗮 𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻. A solution that enables us to serve our clients with the excellence they deserve. 𝗔𝗽𝗽𝗲𝗮𝗹 𝘁𝗼 𝗽𝗿𝗼𝘃𝗶𝗱𝗲 𝘂𝘀 𝗚𝗹𝗶𝘁𝗰𝗵𝗲𝘀 𝗙𝗿𝗲𝗲, 𝗦𝗺𝗼𝗼𝘁𝗵 𝗙𝘂𝗻𝗰𝘁𝗶𝗼𝗻𝗶𝗻𝗴 𝗜𝗻𝗰𝗼𝗺𝗲 𝗧𝗮𝘅 𝗣𝗼𝗿𝘁𝗮𝗹. To the Indian Income Tax Department and the Government, we ask for your support. Help us maintain our professional integrity and the trust of those we serve by ensuring the technology we rely on is robust and dependable. Thanks and Regards Raja Abhishek 9810638155

Abhishek Raja "Ram"

24,529 görüntüleme • 1 yıl önce

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,554 görüntüleme • 6 ay önce

What does the reputation model look like for agents? (alpha leak below) And how do we associate the proofs that we have about human beings with the agents who represent them? You may have heard of a process called KYC or Know Your Customer. That's very common with traditional financial applications and services. We have introduced a concept that we call KYA or Know Your Agent, which is a structured way to be able to express what model, how data was used in training, who the deployer is, what entities this agent instance is accountable back to, providing not only provenance but identity of the associated organization or entity. That's also another root of trust that we think about a lot: Enterprises and organizations tied back to things like their domains. To share a little bit of an alpha leak here, a product that we're excited to be rolling out in the next few weeks will allow our enterprise partners to more easily verify and prove the traits and capabilities of their teams as well as their counterparties. On the agent front, that makes it really easy to prove that an agent is acting on behalf of a given business or entity. We've already seen lawsuits where the absence of such technology has been a huge risk, such as with airlines that incorporate ChatGPT wrappers in their support pages. And then those AI enabled interactions end up making up plane tickets that don't exist and those airlines have to honor them. As small of an example as that might be, being able to prove agent accountability also unlocks a huge set of opportunities for use in enterprise for those agent to agent interactions. The Deep Trust Framework that our team has put together that we're excited to be bringing into a friendly SDK form in the next few weeks for some of our partners includes those reputation based capabilities, so how you can basically keep track of the interactions an agent has had, associate all of that to the entity to which they're accountable, and then that creates a sustainable reputation model for these agent to agent Interactions. Source: Billions CEO Evin McMullen evin speaking at House of Chimera Spaces Event Dec 3, 2025

What does the reputation model look like for agents? (alpha leak below) And how do we associate the proofs that we have about human beings with the agents who represent them? You may have heard of a process called KYC or Know Your Customer. That's very common with traditional financial applications and services. We have introduced a concept that we call KYA or Know Your Agent, which is a structured way to be able to express what model, how data was used in training, who the deployer is, what entities this agent instance is accountable back to, providing not only provenance but identity of the associated organization or entity. That's also another root of trust that we think about a lot: Enterprises and organizations tied back to things like their domains. To share a little bit of an alpha leak here, a product that we're excited to be rolling out in the next few weeks will allow our enterprise partners to more easily verify and prove the traits and capabilities of their teams as well as their counterparties. On the agent front, that makes it really easy to prove that an agent is acting on behalf of a given business or entity. We've already seen lawsuits where the absence of such technology has been a huge risk, such as with airlines that incorporate ChatGPT wrappers in their support pages. And then those AI enabled interactions end up making up plane tickets that don't exist and those airlines have to honor them. As small of an example as that might be, being able to prove agent accountability also unlocks a huge set of opportunities for use in enterprise for those agent to agent interactions. The Deep Trust Framework that our team has put together that we're excited to be bringing into a friendly SDK form in the next few weeks for some of our partners includes those reputation based capabilities, so how you can basically keep track of the interactions an agent has had, associate all of that to the entity to which they're accountable, and then that creates a sustainable reputation model for these agent to agent Interactions. Source: Billions CEO Evin McMullen evin speaking at House of Chimera Spaces Event Dec 3, 2025

Billions

68,458 görüntüleme • 7 ay önce

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

Andrew Ng

107,548 görüntüleme • 1 yıl önce