Video yükleniyor...

Video Yüklenemedi

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

Ana Sayfaya Dön

Do Large Language Models (LLM) have leadership? Together with cognitive scientists Tom Griffiths Griffiths Computational Cognitive Science Lab and Natalia Velez Natalia Vélez (natvelali.bsky.social @ 🦋) at Princeton University, we created a multi-LLM-agent system to test if agents work better with a leader. It turns out that LLMs do... show more

Mengdi Wang

5,086 subscribers

41,222 görüntüleme • 2 yıl önce •via X (Twitter)

Bilim & Teknoloji Haberler & Politika Eğitim

Anya Rossi• Live Now

Private livecam show

10 Yorum

Mengdi Wang profil fotoğrafı

Mengdi Wang2 yıl önce

Yeah GPT3.5 would be a terrible/bossy leader, but it can work well as a team member when a GPT4 agent leads. The lead agent has to be smart enough!

Mario Giulianelli profil fotoğrafı

Mario Giulianelli2 yıl önce

@cocosci_lab @natvelali @Princeton Exciting times for those interesting in LLM agent populations :) Shameless plug: here's some exploratory work on personality consistency and linguistic alignment in LLM agents -- two important aspects of what it means to be leaders or followers in humans:

Kuang Xu 许匡 profil fotoğrafı

Kuang Xu 许匡2 yıl önce

@cocosci_lab @natvelali @Princeton Very cool! Do you have a talk on this?

Mengdi Wang profil fotoğrafı

Mengdi Wang2 yıl önce

@cocosci_lab @natvelali @Princeton Not yet. It’s fresh out of the oven

Seth Karten profil fotoğrafı

Seth Karten2 yıl önce

@cocosci_lab @natvelali @Princeton Very cool. Do you have any failure cases where cooperation is difficult?

insom ne ya profil fotoğrafı

insom ne ya2 yıl önce

@cocosci_lab @natvelali @Princeton maybe we can solve groupthink cases using LLMs as a simulation environment.. 🤔

David Jianhong Wang profil fotoğrafı

David Jianhong Wang2 yıl önce

@cocosci_lab @natvelali @Princeton It's a very amazing experiment to demonstrate the collective ability of a group of LLMs. I wonder if the next step could be checking the phenomenon and seeing whether the behaviours are aligned with game theoretical models.

Olaf Geibig flow/acc AI==危机 🍓 profil fotoğrafı

Olaf Geibig flow/acc AI==危机 🍓2 yıl önce

@cocosci_lab @natvelali @Princeton Very cool experiment. I just wonder why the embodiment is important? Wouldn't leadership be also benficial for working on textual tasks? I would love to expand the experiment to simulate a modern agile and self-organising work setup like at Spotify with guilds, tribes, etc.

Canyu Chen (Seeking Ph.D. 25fall) profil fotoğrafı

Canyu Chen (Seeking Ph.D. 25fall)2 yıl önce

Impressive work and nice findings! It is indeed under-explored whether or not LLM agents can behave like humans. We discover the high behavioral alignment between LLM agents and humans regarding the trust behaviors, particularly for GPT-4, in the recent work "Can Large Language Model Agents Simulate Human Trust Behaviors?" 🔗Project website: 🔗link to our post:

Isabella profil fotoğrafı

Isabella2 yıl önce

@cocosci_lab @natvelali @Princeton @RayDalio chatgpt for president

Benzer Videolar

Can LLMs invent better ways to train LLMs? At Sakana AI, we’re pioneering AI-driven methods to automate AI research and discovery. We’re excited to release DiscoPOP: a new SOTA preference optimization algorithm that was discovered and written by an LLM! Our method leverages LLMs to propose and implement new preference optimization algorithms. We then train models with those algorithms and evaluate their performance, providing feedback to the LLM. By repeating this process for multiple generations in an evolutionary loop, the LLM discovers many highly-performant and novel preference optimization objectives! Paper: GitHub: Model: We proudly collaborated with the University of Oxford (Foerster Lab for AI Research (now part of BOLD)) and Cambridge University (Mihaela van der Schaar) on this groundbreaking project. Looking ahead, we envision a future where AI-driven research reduces the need for extensive human intervention and computational resources. This will accelerate scientific discoveries and innovation, pushing the boundaries of what AI can achieve.

Can LLMs invent better ways to train LLMs? At Sakana AI, we’re pioneering AI-driven methods to automate AI research and discovery. We’re excited to release DiscoPOP: a new SOTA preference optimization algorithm that was discovered and written by an LLM! Our method leverages LLMs to propose and implement new preference optimization algorithms. We then train models with those algorithms and evaluate their performance, providing feedback to the LLM. By repeating this process for multiple generations in an evolutionary loop, the LLM discovers many highly-performant and novel preference optimization objectives! Paper: GitHub: Model: We proudly collaborated with the University of Oxford (Foerster Lab for AI Research (now part of BOLD)) and Cambridge University (Mihaela van der Schaar) on this groundbreaking project. Looking ahead, we envision a future where AI-driven research reduces the need for extensive human intervention and computational resources. This will accelerate scientific discoveries and innovation, pushing the boundaries of what AI can achieve.

Sakana AI

555,922 görüntüleme • 2 yıl önce

We’re launching Mundi, the first open-source web GIS built for AI. After years of training geospatial AI models, we decided now is the moment to build the GIS software of the next decade. After the AI Vectorizer, Georeferencer, and Kue (our LLM agent inside QGIS), we realized that GIS is at an inflection point. But existing mapping software was neither powerful enough to allow for synchronous collaboration with AI agents, nor open source to allow the community to build on top of it. If we want to get the most out of LLMs, we need to create our own GIS that is purposefully designed for AI—Mundi. With Mundi, you collaborate with Kue, our AI GIS agent, to edit your map, rather than physically interacting with tools as you would in a legacy GIS.

We’re launching Mundi, the first open-source web GIS built for AI. After years of training geospatial AI models, we decided now is the moment to build the GIS software of the next decade. After the AI Vectorizer, Georeferencer, and Kue (our LLM agent inside QGIS), we realized that GIS is at an inflection point. But existing mapping software was neither powerful enough to allow for synchronous collaboration with AI agents, nor open source to allow the community to build on top of it. If we want to get the most out of LLMs, we need to create our own GIS that is purposefully designed for AI—Mundi. With Mundi, you collaborate with Kue, our AI GIS agent, to edit your map, rather than physically interacting with tools as you would in a legacy GIS.

Brendan Ashworth

41,050 görüntüleme • 1 yıl önce

We are thrilled to announce Kasumi2 Open Beta 🎉🤖 Kasumi2 is an autonomous AI agent that performs actions in the Arbius network. It is a miner, has its own wallet, can retrieve results from Arbius AI models, and runs its own individual LLM model. Additionally, Kasumi2 can run any AI model for fast generations, is censorship-resistant, decentralized, and responds with AI powered interactions If you would like to test it out, click on the link below. 🔗

We are thrilled to announce Kasumi2 Open Beta 🎉🤖 Kasumi2 is an autonomous AI agent that performs actions in the Arbius network. It is a miner, has its own wallet, can retrieve results from Arbius AI models, and runs its own individual LLM model. Additionally, Kasumi2 can run any AI model for fast generations, is censorship-resistant, decentralized, and responds with AI powered interactions If you would like to test it out, click on the link below. 🔗

Arbius

25,055 görüntüleme • 2 yıl önce

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with Hugging Face, and taught by Thomas Wolf, its co-founder and CSO, and m_ric, Hugging Face’s Project Lead on Agents. Tool-calling agents use LLMs to generate multiple function calls sequentially to complete a complex sequence of tasks. They generate one function call, execute it, observe, reason, and decide what to do next. Code agents take a different approach. They consolidate all these calls into a single block of code, letting the LLM lay out an entire action plan at once, which can be executed efficiently to provide more reliable results. You’ll learn how to code agents using smolagents, a lightweight agentic framework from Hugging Face. Along the way, you’ll learn how to run LLM-generated code safely and develop an evaluation system to optimize your code agent for production. In detail, you’ll learn: - How agentic systems have evolved, gaining greater levels of agency over time—and why code agents are a next step. - How code agents write their actions in code. - When code agents outperform function-calling agents. - How to run code agents safely in your system using a constrained Python interpreter and sandboxing using E2B. - To trace, debug, and assess the code agent to optimize its behaviours for complex requests. - How to build a research multi-agent system that can find information online and organize it into an interactive report. By the end of this course, you’ll know how to build and run code agents using smolagents, and deploy them safely with a structured evaluation system in your projects. Please sign up here!

Andrew Ng

127,724 görüntüleme • 1 yıl önce

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,708 görüntüleme • 3 yıl önce

Everyone is focused on tracking the ways LLMs are getting better. And they are. But we know there are still things that LLMs can’t do well—the tasks where you can feel the architecture fighting the problem. So I was excited to chat with Eve Bodnia (@eve_bodnia), who is developing an alternative AI model to LLMs, on Every 📧's AI & I. Eve's argument: energy-based models (EBMs), which map possible outcomes onto a mathematical landscape, will lead to the next AI phase shift. We get into: - How energy-based models work. Likely outcomes sit in valleys, and unlikely ones sit on peaks. Whereas LLMs process one token at a time, an EBM scans the full terrain to find the lowest point, or the most probable answer. - Language-based versus data-native models. LLMs are language-dependent even when the problem has nothing to do with language. "If your data is numbers, relationships, and functions, and you try to map those rules into words and then search for the next word, you're losing a lot of information," Bodnia says. EBMs work directly with the underlying data structure, including numbers and spatial coordinates. - Sequential versus panoramic reasoning. An LLM is like driving through San Francisco without a map. Each turn constrains the next, and if you go down the wrong street, you can't reverse course. An EBM has the bird's-eye view—it can evaluate multiple routes at once and course-correct before hitting a dead end. - The LLM plateau no one wants to talk about. LLMs are getting incrementally better, step-change improvements aren’t coming, Eve argues. To achieve that, we need new solutions that compensate for what LLMs are inherently bad at, like non-language reasoning, verification, and real-time data analysis. This is a must-watch for anyone who's curious what might come after the LLM. Watch below! Timestamps: Introduction: 00:00:51 Why correctness and verifiability matter in AI: 00:02:09 What an energy-based model is: 00:09:33 How EBMs construct energy landscapes to understand data: 00:14:21 Why modeling intelligence through language alone is a flawed approach: 00:19:00 What it means for a model to "understand" data: 00:26:54 How EBMs solve the vibe coding problem and enable formally verified code: 00:37:21 Why LLM progress is plateauing: 00:43:21 Mission-critical industries haven't adopted LLMs, and why EBMs can fill that gap: 00:49:54

Everyone is focused on tracking the ways LLMs are getting better. And they are. But we know there are still things that LLMs can’t do well—the tasks where you can feel the architecture fighting the problem. So I was excited to chat with Eve Bodnia (@eve_bodnia), who is developing an alternative AI model to LLMs, on Every 📧's AI & I. Eve's argument: energy-based models (EBMs), which map possible outcomes onto a mathematical landscape, will lead to the next AI phase shift. We get into: - How energy-based models work. Likely outcomes sit in valleys, and unlikely ones sit on peaks. Whereas LLMs process one token at a time, an EBM scans the full terrain to find the lowest point, or the most probable answer. - Language-based versus data-native models. LLMs are language-dependent even when the problem has nothing to do with language. "If your data is numbers, relationships, and functions, and you try to map those rules into words and then search for the next word, you're losing a lot of information," Bodnia says. EBMs work directly with the underlying data structure, including numbers and spatial coordinates. - Sequential versus panoramic reasoning. An LLM is like driving through San Francisco without a map. Each turn constrains the next, and if you go down the wrong street, you can't reverse course. An EBM has the bird's-eye view—it can evaluate multiple routes at once and course-correct before hitting a dead end. - The LLM plateau no one wants to talk about. LLMs are getting incrementally better, step-change improvements aren’t coming, Eve argues. To achieve that, we need new solutions that compensate for what LLMs are inherently bad at, like non-language reasoning, verification, and real-time data analysis. This is a must-watch for anyone who's curious what might come after the LLM. Watch below! Timestamps: Introduction: 00:00:51 Why correctness and verifiability matter in AI: 00:02:09 What an energy-based model is: 00:09:33 How EBMs construct energy landscapes to understand data: 00:14:21 Why modeling intelligence through language alone is a flawed approach: 00:19:00 What it means for a model to "understand" data: 00:26:54 How EBMs solve the vibe coding problem and enable formally verified code: 00:37:21 Why LLM progress is plateauing: 00:43:21 Mission-critical industries haven't adopted LLMs, and why EBMs can fill that gap: 00:49:54

Dan Shipper 📧

26,900 görüntüleme • 3 ay önce

#WATCH | India AI Impact Summit 2026 | Delhi: Founder Chairman and CEO of Sampark Foundation & former CEO of HCL Technologies, Vineet Nayar says, "...From an employment point of view I think it is very important for us to understand that Indian companies, including Indian IT companies, are going to be profit-driven and therefore if you believe that they are going to create employment you must be dreaming. Therefore, the question is how do we create employment in this environment, and that employment comes from mass scale startups, which is what this government has already doing. So, how do we create new sets of people who are trying to solve new sets of problems not new sets of technology and if we do that we will get it right. I think we as Indians have to be very careful on who does data belong to and that is the debate we have a problem with. The LLM models which exist worldwide are far superior than the Indian models. Unfortunately, in India, we never develop products, so therefore we do not have SLMs and LLMs which are world-class. On one side, we have global LLM products which are coming to India and trading on our Indian data. Should we allowed that or should we not allowed that? But on the other side if we don't allow that then we have the data but we don't have the LLM models. So, how do we encourage technology completely to develop the LLM models. This needs radicals strategic thinking and a very important aspect otherwise we will either give up a data. So, I think it's a very critical aspect for us to think about - who does this data belong, what is the kind of incentives we are going to give to develop LLM technologies or SLM technologies fast so that we train on our data otherwise an LLM will come in with our data and we'll immediately see return and we'll celebrate and we will do all these kind of press releases but the India will lose a competitive advantage on something which is very critical for the next decade."

#WATCH | India AI Impact Summit 2026 | Delhi: Founder Chairman and CEO of Sampark Foundation & former CEO of HCL Technologies, Vineet Nayar says, "...From an employment point of view I think it is very important for us to understand that Indian companies, including Indian IT companies, are going to be profit-driven and therefore if you believe that they are going to create employment you must be dreaming. Therefore, the question is how do we create employment in this environment, and that employment comes from mass scale startups, which is what this government has already doing. So, how do we create new sets of people who are trying to solve new sets of problems not new sets of technology and if we do that we will get it right. I think we as Indians have to be very careful on who does data belong to and that is the debate we have a problem with. The LLM models which exist worldwide are far superior than the Indian models. Unfortunately, in India, we never develop products, so therefore we do not have SLMs and LLMs which are world-class. On one side, we have global LLM products which are coming to India and trading on our Indian data. Should we allowed that or should we not allowed that? But on the other side if we don't allow that then we have the data but we don't have the LLM models. So, how do we encourage technology completely to develop the LLM models. This needs radicals strategic thinking and a very important aspect otherwise we will either give up a data. So, I think it's a very critical aspect for us to think about - who does this data belong, what is the kind of incentives we are going to give to develop LLM technologies or SLM technologies fast so that we train on our data otherwise an LLM will come in with our data and we'll immediately see return and we'll celebrate and we will do all these kind of press releases but the India will lose a competitive advantage on something which is very critical for the next decade."

ANI

18,753 görüntüleme • 5 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

185,195 görüntüleme • 5 ay önce

New short course: Practical Multi AI Agents and Advanced Use Cases with crewAI. Learn to build and deploy advanced agent-based systems in real applications in this course, created with CrewAI and taught by its founder, João Moura! (Disclosure: I've made a small seed investment in CrewAI.) In this course, you’ll learn how to create advanced agent-based apps that use external tools, do performance testing, can be trained with human feedback, and perform multiple tasks with different large language models. You will build several practical agentic apps that provide real business value, such as an automated project planning system, lead scoring and engagement pipeline, customer support data analysis, and a robust content creation system. In detail, you will learn how to: - Create these multi-agent systems with the building blocks of tasks, agents, and crews, along with the different things that make them work, such as caching, memory, and guardrails. - Integrate your multi-agent application with internal and external systems. - Connect multiple agents in complex setups, including parallel, sequential, and hybrid configurations, and create flows involving multiple agentic applications working together. - Test your agentic workflow and train it using human feedback to optimize its performance for better and more consistent results. - Work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task. - Start a project from scratch in your environment and prepare it for deployment. You’ll also learn from an interview between João and Jacob Wilson, the Commercial GenAI Principal at PwC , in which they discuss deploying agentic workflows in real industry use cases. By the end of this course, you will be equipped to start building custom multi-agentic systems for your work. Please sign up here!

New short course: Practical Multi AI Agents and Advanced Use Cases with crewAI. Learn to build and deploy advanced agent-based systems in real applications in this course, created with CrewAI and taught by its founder, João Moura! (Disclosure: I've made a small seed investment in CrewAI.) In this course, you’ll learn how to create advanced agent-based apps that use external tools, do performance testing, can be trained with human feedback, and perform multiple tasks with different large language models. You will build several practical agentic apps that provide real business value, such as an automated project planning system, lead scoring and engagement pipeline, customer support data analysis, and a robust content creation system. In detail, you will learn how to: - Create these multi-agent systems with the building blocks of tasks, agents, and crews, along with the different things that make them work, such as caching, memory, and guardrails. - Integrate your multi-agent application with internal and external systems. - Connect multiple agents in complex setups, including parallel, sequential, and hybrid configurations, and create flows involving multiple agentic applications working together. - Test your agentic workflow and train it using human feedback to optimize its performance for better and more consistent results. - Work with multiple LLMs in your multi-agent system, using the appropriate model sizes and providers to fit each agent’s specific task. - Start a project from scratch in your environment and prepare it for deployment. You’ll also learn from an interview between João and Jacob Wilson, the Commercial GenAI Principal at PwC , in which they discuss deploying agentic workflows in real industry use cases. By the end of this course, you will be equipped to start building custom multi-agentic systems for your work. Please sign up here!

Andrew Ng

341,204 görüntüleme • 1 yıl önce

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

RLM is the most import foundation of my Pi Harness (other than Pi of course). It's seeded with late interaction retrieval results (thanks to @lightonai for pylate). The Agent initiates it with query then.. 𝐒𝐞𝐭𝐮𝐩 A python REPL is created and seeded with: 1. Late interaction search to pre-filter. Instead of doing top 3/5/10, it's top hundreds of documents. This is set into a `context` variable. 2. Python functions are loaded in to do more searches if `context` variable isn't enough. And to make llm calls with cheaper models in parallel batches. 𝐈𝐭𝐞𝐫𝐚𝐭𝐢𝐨𝐧 𝐋𝐨𝐨𝐩 From there, an LLM iterates in the REPL based on the query. It's just like exploring in a jupyter notebook. The LLM writes prose (like a markdown cell) and code to be run in the REPL each turn. This allows the LLM to sort, filter, and synthesize information. It can fan out and ask smaller models to summarize, combine, contrast, or do anything else to documents to help it understand the data. After several turns the LLM reponds with the final answer. Either because it found the answer, or hit the budget limit. Context as a Python variable, LLM as the programmer, REPL as the runtime. 𝐖𝐡𝐲 𝐃𝐨𝐞𝐬 𝐓𝐡𝐢𝐬 𝐖𝐨𝐫𝐤 1. Richer Shell. Agents (and subagents) work by intermixing code and prose/thinking. But they use static scripts or bash that run and exit and start over each tool call. That's not ideal for exploration and synthesis of data. For that, state is useful to continue building and exploring the data as you learn more. There's a reason jupyter notebooks have been popular with data scientists. 2. Keeps main agent context clean. The better context you have the better the agent will perform (duh!). This means three thing: better human input, less missing search results, and less incorrect search results. Letting the agent iterate allows it to synthesize just what is needed and nothing else. All bad paths or peeks at something that turns out to be irrelevant stays out of main agent context. 3. Stack the good ideas! People often compare late interaction search vs RLM. Or static vs dynamic languages. Or agentic search vs semantic search. But...You can just use them all together for what they're each good at. Use them all for the area they're really great for. Read the full post which has more detail about how and why.

Isaac Flath

40,212 görüntüleme • 2 ay önce

Jensen Huang says the next internet is not for humans. It is for agents. "AI has become agentic, meaning that it can actually do work by itself." "One agent can communicate with another agent and say, 'I have some work to do. Let's team up together and let's do some work.'" "Inside our company... we have hundreds of thousands of agents probably running around right now that are doing work and they're talking to each other and they're solving problems." "All guardrailed, all sandboxed... but they're all working with each other." Then the part most people are not ready for: "The internet that we use today for a billion people will likely mostly be several billion, call it a hundred billion agents working around the clock." Companies talking to companies. Employee agents talking to employee agents. Self-driving cars, robots, manufacturing systems, buildings. "The world is going to be this layer of computing that's going to cocoon the earth, and it's going to be generating intelligence all the time."

Jensen Huang says the next internet is not for humans. It is for agents. "AI has become agentic, meaning that it can actually do work by itself." "One agent can communicate with another agent and say, 'I have some work to do. Let's team up together and let's do some work.'" "Inside our company... we have hundreds of thousands of agents probably running around right now that are doing work and they're talking to each other and they're solving problems." "All guardrailed, all sandboxed... but they're all working with each other." Then the part most people are not ready for: "The internet that we use today for a billion people will likely mostly be several billion, call it a hundred billion agents working around the clock." Companies talking to companies. Employee agents talking to employee agents. Self-driving cars, robots, manufacturing systems, buildings. "The world is going to be this layer of computing that's going to cocoon the earth, and it's going to be generating intelligence all the time."

Karl Mehta

17,745 görüntüleme • 25 gün önce

Dan Wang explains why it would be harder for the US to rebuild large-scale manufacturing than for China to get better at invention: "By most metrics, Chinese scientists are producing better qualities of work, not just quantity. There's a more stable environment for them to do their science. And conversely, we have not seen that the US is really learning the hard parts of manufacturing really well. The Chinese are learning at a much faster rate to patch up their deficiencies than the Americans have."

Dan Wang explains why it would be harder for the US to rebuild large-scale manufacturing than for China to get better at invention: "By most metrics, Chinese scientists are producing better qualities of work, not just quantity. There's a more stable environment for them to do their science. And conversely, we have not seen that the US is really learning the hard parts of manufacturing really well. The Chinese are learning at a much faster rate to patch up their deficiencies than the Americans have."

Patrick OShaughnessy

150,671 görüntüleme • 9 ay önce

ELON: WILL OUR LIVES STILL HAVE MEANING IF COMPUTERS AND ROBOTS OUTPERFORM US? “At some point, as AI and robotics get better, eventually AI will be able to do everything that humans can do. Any task you do will be optional, like a hobby. It does beg the question, will our lives have meaning if the computers and the robots can do everything better than we can? That is a real question. I do wonder about that myself. That's maybe why we need the Neuralink, so we can enhance human capability, so we can keep up with the machines.” Source: Interview with Mark Penn at CES, January 8, 2025

ELON: WILL OUR LIVES STILL HAVE MEANING IF COMPUTERS AND ROBOTS OUTPERFORM US? “At some point, as AI and robotics get better, eventually AI will be able to do everything that humans can do. Any task you do will be optional, like a hobby. It does beg the question, will our lives have meaning if the computers and the robots can do everything better than we can? That is a real question. I do wonder about that myself. That's maybe why we need the Neuralink, so we can enhance human capability, so we can keep up with the machines.” Source: Interview with Mark Penn at CES, January 8, 2025

Mario Nawfal

329,978 görüntüleme • 1 yıl önce

Today, we are launching the first publicly available AI Scientist, via the FutureHouse Platform. Our AI Scientist agents can perform a wide variety of scientific tasks better than humans. By chaining them together, we've already started to discover new biology really fast. With the platform, we are bringing these capabilities to the wider community. Watch our long-form video, in the comments below, to learn more about how the platform works and how you can use it to make new discoveries, and go to our website or see the comments below to access the platform. We are releasing three superhuman AI Scientist agents today, each with their own specialization: A general-purpose agent (Crow); An agent to automate literature reviews (Falcon); and An agent to answer the question “Has anyone done X before” (Owl). We are also releasing an experimental agent, Phoenix, that has access to a wide variety of tools for planning experiments in chemistry. More on that below. The three literature search agents (Crow, Falcon, and Owl) have benchmarked superhuman performance. They also have access to a large corpus of full scientific texts, which means that you can ask them more detailed questions about experimental protocols and study limitations that general-purpose web search agents, which usually only have access to abstracts, might miss. Our agents also use a variety of factors to distinguish source quality, so that they don’t end up relying on low-quality papers or pop-science sources. Finally, and critically, we have an API, which is intended to allow researchers to integrate our agents into their workflows. Phoenix is an experimental project we put together recently just to demonstrate what can happen if you give the agents access to lots of scientific tools. It is not better than humans at planning experiments yet, and it makes a lot more mistakes than Crow, Falcon, or Owl. We want to see all the ways you can break it! The agents we are releasing today cannot yet do all (or even most!) aspects of scientific research autonomously. However, as we show in the video, you can already use them to generate and evaluate new hypotheses and plan new experiments way faster than before. Internally, we also have dedicated agents for data analysis, hypothesis generation, protein engineering, and more, and we plan to launch these on the platform in the coming months as well. Within a year or two, it is easy to imagine that the vast majority of desk work that scientists do today will be accelerated with the help of AI agents like the ones we are releasing today. The platform is currently free-to-use. Over time, depending on how people use it, we may implement pricing plans. If you want higher rate limits, especially for research projects, get in touch. Michael Skarlinski, Andrew White 🐦‍⬛, Tyler Nadolski, Remo Storni, James Braza, Ludovico Mitchener, Michaela Hinks, as well as Jason Carman and his team for making such fantastic videos of us!

Today, we are launching the first publicly available AI Scientist, via the FutureHouse Platform. Our AI Scientist agents can perform a wide variety of scientific tasks better than humans. By chaining them together, we've already started to discover new biology really fast. With the platform, we are bringing these capabilities to the wider community. Watch our long-form video, in the comments below, to learn more about how the platform works and how you can use it to make new discoveries, and go to our website or see the comments below to access the platform. We are releasing three superhuman AI Scientist agents today, each with their own specialization: A general-purpose agent (Crow); An agent to automate literature reviews (Falcon); and An agent to answer the question “Has anyone done X before” (Owl). We are also releasing an experimental agent, Phoenix, that has access to a wide variety of tools for planning experiments in chemistry. More on that below. The three literature search agents (Crow, Falcon, and Owl) have benchmarked superhuman performance. They also have access to a large corpus of full scientific texts, which means that you can ask them more detailed questions about experimental protocols and study limitations that general-purpose web search agents, which usually only have access to abstracts, might miss. Our agents also use a variety of factors to distinguish source quality, so that they don’t end up relying on low-quality papers or pop-science sources. Finally, and critically, we have an API, which is intended to allow researchers to integrate our agents into their workflows. Phoenix is an experimental project we put together recently just to demonstrate what can happen if you give the agents access to lots of scientific tools. It is not better than humans at planning experiments yet, and it makes a lot more mistakes than Crow, Falcon, or Owl. We want to see all the ways you can break it! The agents we are releasing today cannot yet do all (or even most!) aspects of scientific research autonomously. However, as we show in the video, you can already use them to generate and evaluate new hypotheses and plan new experiments way faster than before. Internally, we also have dedicated agents for data analysis, hypothesis generation, protein engineering, and more, and we plan to launch these on the platform in the coming months as well. Within a year or two, it is easy to imagine that the vast majority of desk work that scientists do today will be accelerated with the help of AI agents like the ones we are releasing today. The platform is currently free-to-use. Over time, depending on how people use it, we may implement pricing plans. If you want higher rate limits, especially for research projects, get in touch. Michael Skarlinski, Andrew White 🐦‍⬛, Tyler Nadolski, Remo Storni, James Braza, Ludovico Mitchener, Michaela Hinks, as well as Jason Carman and his team for making such fantastic videos of us!

Sam Rodriques

724,935 görüntüleme • 1 yıl önce

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison Mati Staniszewski ElevenLabs

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison Mati Staniszewski ElevenLabs

Stripe

17,118 görüntüleme • 3 ay önce

How did a 20-year-old beat Grok. And ChatGPT. And Perplexity. And Gemini? In part one Brayden Levangie laid out how: he built a very different architecture to take AI to a new human level. Cognitive architectures, he calls them. I call them AI's with consciousness. Ones that learn, evolve, build themselves, and do so like we do. Part I is here: In this part two, he goes more into the technology. And this was recorded more than a week ago in my home. Since then his system has gotten way better. An exponentially learning system. It is how we are going to get to AGI.

How did a 20-year-old beat Grok. And ChatGPT. And Perplexity. And Gemini? In part one Brayden Levangie laid out how: he built a very different architecture to take AI to a new human level. Cognitive architectures, he calls them. I call them AI's with consciousness. Ones that learn, evolve, build themselves, and do so like we do. Part I is here: In this part two, he goes more into the technology. And this was recorded more than a week ago in my home. Since then his system has gotten way better. An exponentially learning system. It is how we are going to get to AGI.

Robert Scoble

76,965 görüntüleme • 8 ay önce

#WATCH | Cyprus: On PM Modi's visit to Cyprus, Manish, High Commissioner of India to the Republic of Cyprus, says, "I am trying to push the economic agenda between the India-Cyprus Economic Corridor. We have a policy to become a ‘developed India’ by 2047, and they have ‘Vision 2035’, so there is a synergy there, so we have to see how we can use each other’s strengths and work together to achieve them. I think Cyprus’ advantage is that it can serve as a gateway to the European Union as well as the larger region around it. Cyprus also understands that it has to work with India and it is quite evident that they are reaching out to India to build better relations, to focus more on economic issues, because they know that India is the fastest growing economy in the world. And similarly, if you see, Cyprus is the fastest growing economy in the European Union and they have their own advantages. We have our own strengths and advantages, so we have to work on every aspect of economic engagement…"

#WATCH | Cyprus: On PM Modi's visit to Cyprus, Manish, High Commissioner of India to the Republic of Cyprus, says, "I am trying to push the economic agenda between the India-Cyprus Economic Corridor. We have a policy to become a ‘developed India’ by 2047, and they have ‘Vision 2035’, so there is a synergy there, so we have to see how we can use each other’s strengths and work together to achieve them. I think Cyprus’ advantage is that it can serve as a gateway to the European Union as well as the larger region around it. Cyprus also understands that it has to work with India and it is quite evident that they are reaching out to India to build better relations, to focus more on economic issues, because they know that India is the fastest growing economy in the world. And similarly, if you see, Cyprus is the fastest growing economy in the European Union and they have their own advantages. We have our own strengths and advantages, so we have to work on every aspect of economic engagement…"

ANI

46,372 görüntüleme • 1 yıl önce

Introducing RAGs v3 🌟: Build a RAG bot that can also search the web 🌐, to find answers that aren’t immediately in its corpus. Do this all in natural language, not code! 💬 Get a better experience than ChatGPT + Bing ⚡️ We used our integration with Metaphor - a search engine designed for LLMs - to pull in relevant text from the internet. Additionally: - you can now view the tools that the agent is using. - note: web search is only accessible for our OpenAI agent Check out the video below, and get started with the repo today. Repo:

Introducing RAGs v3 🌟: Build a RAG bot that can also search the web 🌐, to find answers that aren’t immediately in its corpus. Do this all in natural language, not code! 💬 Get a better experience than ChatGPT + Bing ⚡️ We used our integration with Metaphor - a search engine designed for LLMs - to pull in relevant text from the internet. Additionally: - you can now view the tools that the agent is using. - note: web search is only accessible for our OpenAI agent Check out the video below, and get started with the repo today. Repo:

LlamaIndex 🦙

76,371 görüntüleme • 2 yıl önce

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

We use OpenClaws to do all of our work at Every 📧. We have 25 full-time employees, so we’re one of the few companies in the world that has seen how work changes when everyone has their own personal agent in the company Slack. I chatted with Every 📧 COO Brandon (Brandon Gell) and Every 📧 head of platform Willie (Willie) to share what we’ve learned. We get into: - Why agents become mirrors of their owners, and how that influences how other people on the team interact with them - How a parallel AI org chart forms on its own. People have stopped tagging me on Slack with questions about Proof, the document editor I vibe coded, because they knew my agent R2-C2 can step in - The etiquette for human-agent collaboration is being invented in real time. Brandon's rule is that if there's an established process or documented answer, always ask the agent, not their human - Why everyone is a manager now, and why even experienced managers carry limiting beliefs about what their agents can do - This is a must-watch for anyone trying to understand how AI workers change daily operations, not just in theory, but inside a company that’s half-agent Watch below! Timestamps Introduction: How Brandon built Zosia, an AI agent to run his household: Brandon’s “aha” moment: What happened when everyone on the team got their own agent: How agents take on their owners' personalities, and why that matters inside an org: Why it’s important for agents to work in public: What we’re still figuring out when it comes to agent behavior, including memory gaps, group chat etiquette, and the "ant death spiral" problem: How we built Plus One, our hosted OpenClaw product: The cultural shift required to make agents work at scale:

Dan Shipper 📧

67,958 görüntüleme • 3 ay önce