Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Sub-agents in (latent) space! We’ve been working on a side project. As far as I know, this is the first massively multiplayer, completely LLM-driven game. Come play Gradient Bang with us. See if you can catch me on the leaderboard. This whole thing started because I wanted to explore...

kwindla's profile picture

kwindla

15,714 subscribers

455,977 Aufrufe • vor 4 Monaten •via X (Twitter)

GamingWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!
2:57

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 Aufrufe • vor 1 Jahr

We're only year 3 of a decade (if not multi-decades) long transformation of work. 3 years ago we bet on building an horizontal platform for work with agents, a chance to invent a new operating system for companies, from scratch, with AI as a fundamental premise. Many people considered us crazy for going after that, praising verticalized AI products as the winning strategy. But here's the thing: the time horizon of tasks successfully handled by agents has been predictively increasing form minutes to hours and will in all likelihood reach the equivalent of days and weeks of human work equivalent in the coming quarters. This is were verticalized and/or single-player AI falls short. Single-player tools, one person, one agent, confined to your machine is the wrong architecture for what's coming. We're shifting from using AI to produce things, to managing fleets of agents that do the producing. 3 years ago I wrote[1]: "ChatGPT is the Pong of LLMs. [...] Imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs. Let alone multiplayer modes." Weeks long tasks in companies are inherently collaborative and mechanically spanning multiple teams. The new bottleneck in harnessing agents within organizations is coordination: multiple humans and multiple agents need to work together, with shared context, shared tools, shared goals. Agents that can hand work off to other agents or surface decisions to the right person at the right time. Humans who can review, steer, and step in without losing the thread. Teams that can run parallel workstreams and actually stay aligned. This is Multiplayer AI, and that's what we've been building at Dust. Across Datadog, Clay, Persona, 1Password, Doctolib and 3,000+ organizations globally, we've watched teams figure out what this looks like in practice. 300,000+ agents deployed. 70% weekly active. 240%+ NRR. Today we're announcing a $40M Series B with Abstract, Sequoia, Snowflake, and Datadog to accelerate our vision. Designing the right interfaces for multiplayer AI is the next frontier. Join us to redefine work by defining multiplayer AI.
1:54

We're only year 3 of a decade (if not multi-decades) long transformation of work. 3 years ago we bet on building an horizontal platform for work with agents, a chance to invent a new operating system for companies, from scratch, with AI as a fundamental premise. Many people considered us crazy for going after that, praising verticalized AI products as the winning strategy. But here's the thing: the time horizon of tasks successfully handled by agents has been predictively increasing form minutes to hours and will in all likelihood reach the equivalent of days and weeks of human work equivalent in the coming quarters. This is were verticalized and/or single-player AI falls short. Single-player tools, one person, one agent, confined to your machine is the wrong architecture for what's coming. We're shifting from using AI to produce things, to managing fleets of agents that do the producing. 3 years ago I wrote[1]: "ChatGPT is the Pong of LLMs. [...] Imagine, one day we'll get the DOOM, Civ, Red Alert, and Counter Strike of LLMs. Let alone multiplayer modes." Weeks long tasks in companies are inherently collaborative and mechanically spanning multiple teams. The new bottleneck in harnessing agents within organizations is coordination: multiple humans and multiple agents need to work together, with shared context, shared tools, shared goals. Agents that can hand work off to other agents or surface decisions to the right person at the right time. Humans who can review, steer, and step in without losing the thread. Teams that can run parallel workstreams and actually stay aligned. This is Multiplayer AI, and that's what we've been building at Dust. Across Datadog, Clay, Persona, 1Password, Doctolib and 3,000+ organizations globally, we've watched teams figure out what this looks like in practice. 300,000+ agents deployed. 70% weekly active. 240%+ NRR. Today we're announcing a $40M Series B with Abstract, Sequoia, Snowflake, and Datadog to accelerate our vision. Designing the right interfaces for multiplayer AI is the next frontier. Join us to redefine work by defining multiplayer AI.

Stanislas Polu

1,327,399 Aufrufe • vor 3 Monaten

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:
2:07

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

126,587 Aufrufe • vor 1 Jahr

Here’s why OpenHome creator Jesse Leimgruber says, if you’re still prompting OpenClaw🦞 on a screen, you’re falling behind! The whole point of AI agents is that they can do things for you in the real world. But what’s the point if you’re still interacting with them exclusively through a laptop. That’s why Jesse created a smart speaker that allows you to interact vocally with your agent from any room in your home, 24/7. Having an agent listen in on your conversations, and learn all about you and your life in context, opens up an entirely new level of productivity… and might just save your Valentine’s Day as well.
5:01

Here’s why OpenHome creator Jesse Leimgruber says, if you’re still prompting OpenClaw🦞 on a screen, you’re falling behind! The whole point of AI agents is that they can do things for you in the real world. But what’s the point if you’re still interacting with them exclusively through a laptop. That’s why Jesse created a smart speaker that allows you to interact vocally with your agent from any room in your home, 24/7. Having an agent listen in on your conversations, and learn all about you and your life in context, opens up an entirely new level of productivity… and might just save your Valentine’s Day as well.

This Week in Startups

209,839 Aufrufe • vor 6 Monaten

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...
3:28

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...

kwindla

324,083 Aufrufe • vor 8 Tagen

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!
2:55

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

27,570 Aufrufe • vor 3 Monaten

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.
1:24

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,679 Aufrufe • vor 8 Monaten

Building with AI gets easier every day. Here is an open-source library that makes integrating AI into an application extremely easy: Star the repository! This library alone can make React the best front-end framework out there! There are a bunch of cool things I like about CopilotKit. Here are 3 of them: 1. It allows you to take any -powered agent and bring it into your application. (This is a brand-new feature!) 2. You can build an AI-powered chatbot in your application. The chatbot will have access to your context and can act on the application. 3. You can build a RAG workflow to process and answer questions from a real-time knowledge base. I recorded a video to show you how simple it is to make some of this happen. A few lines of code, and you are in business. Here is a link to the sample application: CopilotKit is open-source. You can self-host it. You can use it with any LLM. Thanks to the team for showing me their tool and collaborating with me on this post!
5:59

Building with AI gets easier every day. Here is an open-source library that makes integrating AI into an application extremely easy: Star the repository! This library alone can make React the best front-end framework out there! There are a bunch of cool things I like about CopilotKit. Here are 3 of them: 1. It allows you to take any -powered agent and bring it into your application. (This is a brand-new feature!) 2. You can build an AI-powered chatbot in your application. The chatbot will have access to your context and can act on the application. 3. You can build a RAG workflow to process and answer questions from a real-time knowledge base. I recorded a video to show you how simple it is to make some of this happen. A few lines of code, and you are in business. Here is a link to the sample application: CopilotKit is open-source. You can self-host it. You can use it with any LLM. Thanks to the team for showing me their tool and collaborating with me on this post!

Santiago

108,835 Aufrufe • vor 2 Jahren

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.
0:22

AG-UI makes building agentic applications dramatically easier. Here's how it works. This is a model for a simple chatbot: User → LLM → Response But interactive agents that render UI, pause for approvals, and ask users for input need a much more complex model. When building these agents, a response from the LLM will include a series of state changes as the agent runs: • Agent started a task • Agent called a tool • Agent updated its state • Agent streams these tokens • Agent is waiting on a human • Agent is resuming the task The Agent-User Interaction Protocol (AG-UI) treats the LLM response as a stream of events rather than a text endpoint. In practice, here is what you get as an agent runs: 1. Lifecycle events so your UI knows where the agent is. 2. Text messages that stream tokens. 3. Tool calls so your UI can prefill a form with any required arguments. 4. State updates that keep your UI in sync with the agent. 5. Special events for human approvals, rich media, and custom needs. All of these events travel over standard transports (SSE, WebSockets, or plain HTTP) as JSON. As a result, you can build a frontend that stays in sync with the agent's progress without having to invent a custom process to make this happen. For example, building a human-in-the-loop workflow becomes an off-the-shelf component you can integrate rather than build from scratch. CopilotKit🪁 is the creator of AG-UI, and you can use it when building frontend applications pretty much anywhere: • React • Angular • Vue • React Native • Slack • Teams • Discord • WhatsApp • Telegram Here is the link for you to check it out: Thanks to the CopilotKit team for partnering with me on this post.

Santiago

17,438 Aufrufe • vor 2 Monaten

introducing kenkyu kenkyu is an autonomous research agent that I made a while back. it is designed to transform a single user query into a comprehensive, structured report. how it works : - it takes user input as query - plans the next course of action - researches about the plan created using tavily - synthesis the collected information into a detailed final response it functions by orchestrating a multi agent workflow that mimics the steps of a human researcher , but at a much higher speed and scale. this is the v0 prototype, currently open source as of now and i have a lot of things planned that i want to add it in the future.
1:47

introducing kenkyu kenkyu is an autonomous research agent that I made a while back. it is designed to transform a single user query into a comprehensive, structured report. how it works : - it takes user input as query - plans the next course of action - researches about the plan created using tavily - synthesis the collected information into a detailed final response it functions by orchestrating a multi agent workflow that mimics the steps of a human researcher , but at a much higher speed and scale. this is the v0 prototype, currently open source as of now and i have a lot of things planned that i want to add it in the future.

sharpeye

35,183 Aufrufe • vor 6 Monaten

The danger of AI is not just the slop, but what we lose in the process. Michael Pollan explains: "We're moving into this time where we're gonna sub out writing to AI. And AI can write our papers, and professors are dealing with this everywhere now. But what is lost is a way of thinking. Writing does something to your brain. It gives you access to things you can't know just walking around or thinking or planning or outlining. If you were just transcribing what was in your head, it would be kind of onerous. But it really is what you learn in the course of a day spent writing, things you didn't know, ideas that you didn't expect. And that's the thrill of it."
1:20

The danger of AI is not just the slop, but what we lose in the process. Michael Pollan explains: "We're moving into this time where we're gonna sub out writing to AI. And AI can write our papers, and professors are dealing with this everywhere now. But what is lost is a way of thinking. Writing does something to your brain. It gives you access to things you can't know just walking around or thinking or planning or outlining. If you were just transcribing what was in your head, it would be kind of onerous. But it really is what you learn in the course of a day spent writing, things you didn't know, ideas that you didn't expect. And that's the thrill of it."

David Perell Clips

18,468 Aufrufe • vor 2 Monaten

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.
3:38

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Santiago

230,647 Aufrufe • vor 1 Jahr

I'm up late with the rest of you building AI agents with the new AI browser from Genspark. We can see where this is all going: a new kind of operating system -- one that is very different than the Microsoft centric way that I've been working for 20 years. There are several things that these new agentic browsers bring to you: 1. They let you change how you browse. With an old browser like Google Chrome, you go to your email, Facebook, or X. 2. With these new browsers, you tell it where to go and what to do for you. 3. It can even build software for you. At the end of this video, I have it building me a little YouTube uploading utility, which is very helpful. 4. They have a ton of "applications" built in. Think of it as a new kind of office suite. Docs. Spreadsheets. Slide decks. And much more. All built with AI, not bolted on the side like with Microsoft's Office. 5. They have AI models built "underneath" so you can work privately and cheaply. There’s a lot of new choices you have to make with browsers like this. I’ve been playing with a bunch of them. Some have better user interfaces than others. Some have different versions, slide components, or applications. The reason I like Genspark is because they ship so fast. I’ve been watching this company since its very beginnings, and every week they ship new things. Just yesterday, they shipped a new photo editing feature for my iPhone. I upload a photo and then I can just talk to it and edit it with my voice. It's really cool. I try to reward companies that ship at such a fast rate and that are shipping innovation that improves our lives. It's not that I'm going to stop using Google Chrome. My whole life has been there for, I don't know, almost 20 years now. This is a different way of working and it gives me a space to run my AI tasks that's different than Google Chrome. I run them side by side. One doing old stuff, one doing new stuff. I can keep using Google Chrome for my old stuff, like my email and my calendar. And I use GenSpark or one of the new AI browsers to do new AI-centric things. All sorts of new things that these new agentic browsers open up! Have you tried it, or one of the other new ones yet? How has it changed your work? It takes a little time to get used to AI-centric ways of doing things. Pretend your browser is a team of interns. Give them a task, in this case I said "help me upload my videos to YouTube." You might be shocked at what Genspark does to improve your life. I am everytime I use it. Give it a try and let me know what you think! Oh, and I used another little tool to "write" this post. Typeless -- I push a button and talk and it writes. With fewer typos than I usually type in, to boot. It works great with Genspark's new browser too. Download it here:
3:41

I'm up late with the rest of you building AI agents with the new AI browser from Genspark. We can see where this is all going: a new kind of operating system -- one that is very different than the Microsoft centric way that I've been working for 20 years. There are several things that these new agentic browsers bring to you: 1. They let you change how you browse. With an old browser like Google Chrome, you go to your email, Facebook, or X. 2. With these new browsers, you tell it where to go and what to do for you. 3. It can even build software for you. At the end of this video, I have it building me a little YouTube uploading utility, which is very helpful. 4. They have a ton of "applications" built in. Think of it as a new kind of office suite. Docs. Spreadsheets. Slide decks. And much more. All built with AI, not bolted on the side like with Microsoft's Office. 5. They have AI models built "underneath" so you can work privately and cheaply. There’s a lot of new choices you have to make with browsers like this. I’ve been playing with a bunch of them. Some have better user interfaces than others. Some have different versions, slide components, or applications. The reason I like Genspark is because they ship so fast. I’ve been watching this company since its very beginnings, and every week they ship new things. Just yesterday, they shipped a new photo editing feature for my iPhone. I upload a photo and then I can just talk to it and edit it with my voice. It's really cool. I try to reward companies that ship at such a fast rate and that are shipping innovation that improves our lives. It's not that I'm going to stop using Google Chrome. My whole life has been there for, I don't know, almost 20 years now. This is a different way of working and it gives me a space to run my AI tasks that's different than Google Chrome. I run them side by side. One doing old stuff, one doing new stuff. I can keep using Google Chrome for my old stuff, like my email and my calendar. And I use GenSpark or one of the new AI browsers to do new AI-centric things. All sorts of new things that these new agentic browsers open up! Have you tried it, or one of the other new ones yet? How has it changed your work? It takes a little time to get used to AI-centric ways of doing things. Pretend your browser is a team of interns. Give them a task, in this case I said "help me upload my videos to YouTube." You might be shocked at what Genspark does to improve your life. I am everytime I use it. Give it a try and let me know what you think! Oh, and I used another little tool to "write" this post. Typeless -- I push a button and talk and it writes. With fewer typos than I usually type in, to boot. It works great with Genspark's new browser too. Download it here:

Robert Scoble

70,991 Aufrufe • vor 11 Monaten

$RKLB New Peter Beck interview today on Bloomberg: Does SpaceX's dominance threaten Rocket Lab? "No, I don't think so. The reality is SpaceX is a space company, but also very much an AI company and a bunch of other things as well. Rocket Lab is a very squarely focused pure play space company. I think it draws investors into the sector. And when they go looking, Rocket Lab is really the clear number two with respect to launch frequency and those kinds of things. So no, I'm not too worried about that.” "So do you find yourself complementary to SpaceX? Or are you in direct competition with Elon Musk?" "In some cases we are in direct competition, but also very complementary. We are an end-to-end space company. We're the second most frequently launched US rocket in the world behind SpaceX, so the rocket bit is competitive. But two-thirds of our business is building satellites and spacecraft and supplying components to the rest of the space industry. So in that sense, not really a competitor at all."
1:13

$RKLB New Peter Beck interview today on Bloomberg: Does SpaceX's dominance threaten Rocket Lab? "No, I don't think so. The reality is SpaceX is a space company, but also very much an AI company and a bunch of other things as well. Rocket Lab is a very squarely focused pure play space company. I think it draws investors into the sector. And when they go looking, Rocket Lab is really the clear number two with respect to launch frequency and those kinds of things. So no, I'm not too worried about that.” "So do you find yourself complementary to SpaceX? Or are you in direct competition with Elon Musk?" "In some cases we are in direct competition, but also very complementary. We are an end-to-end space company. We're the second most frequently launched US rocket in the world behind SpaceX, so the rocket bit is competitive. But two-thirds of our business is building satellites and spacecraft and supplying components to the rest of the space industry. So in that sense, not really a competitor at all."

ValueOverPrice

51,585 Aufrufe • vor 2 Monaten

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.
0:25

I am hooked on Dynamic Workflows! The idea of generating harnesses on the fly is so compelling that I reverse-engineered it for my agent orchestrator. And then I built a monitoring dashboard (as an HTML artifact) to track tasks, metrics, and reports. I can now use and monitor dynamic workflows in my agent orchestrator with coding agents like Claude Code, Codex, Pi, and even my own custom-built DAIR.AI agent. This is clearly the future of working with agents to accomplish complex, long-running tasks. Some use cases I'm having success with: - Branching deep research tasks (with verification) - Parallel deep research tasks - Session mining of all my agent sessions - Bug hunting - Triaging - Fact-checking - LLM councils - AI simulations - Data synthesis - Evals generation ... and many others Dynamic workflows, like agent skills, feel like an important primitive to not only get the most out of agents but also incorporate dynamic behaviors and important components like cooperation and verification. There is so much exploration ground here. The exciting part is that this is not limited to coding tasks; it extends to business use cases and many other technical domains like science and research.

elvis

103,977 Aufrufe • vor 3 Monaten

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)
0:40

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,593 Aufrufe • vor 3 Monaten

AI agents don’t feel the pain that humans do. 3 takeaways from Mario Zechner(Mario Zechner), creator of Pi - the minimalist, self-modifying agent that OpenClaw is built on: #1 - Automation bias: agents quickly wow us and win false trust: “There are moments of brilliance in agents where they spit out perfectly fine simple code. As the steering engineer you can look at that and think: ‘Wow, this is amazing. I can just sit back and not care because it's doing the thing how I would do it.’ Two minutes later you have another agent running that spits out the worst, horrible, garbage code, but you might not notice because you have fallen into automation bias and think your agent is doing the job well.” #2 - Humans have a different capacity for learning than agents: “Agents don't learn. You can put as much stuff in your AGENTS.md, build a memory system, but it's not the same type of learning that a human does. Humans are failable as well, but they have some capability of learning.” #3 - Feeling pain is inherently human and drives us to make things well: “Humans feel pain. I think that's one of the defining things about humans. If the pain gets too big, you as a human are incentivized to fix the cause of your pain. In a code base, the cause is usually terrible interfaces and terrible complexity that you want to get rid of because you can no longer maintain that system.”
1:53

AI agents don’t feel the pain that humans do. 3 takeaways from Mario Zechner(Mario Zechner), creator of Pi - the minimalist, self-modifying agent that OpenClaw is built on: #1 - Automation bias: agents quickly wow us and win false trust: “There are moments of brilliance in agents where they spit out perfectly fine simple code. As the steering engineer you can look at that and think: ‘Wow, this is amazing. I can just sit back and not care because it's doing the thing how I would do it.’ Two minutes later you have another agent running that spits out the worst, horrible, garbage code, but you might not notice because you have fallen into automation bias and think your agent is doing the job well.” #2 - Humans have a different capacity for learning than agents: “Agents don't learn. You can put as much stuff in your AGENTS.md, build a memory system, but it's not the same type of learning that a human does. Humans are failable as well, but they have some capability of learning.” #3 - Feeling pain is inherently human and drives us to make things well: “Humans feel pain. I think that's one of the defining things about humans. If the pain gets too big, you as a human are incentivized to fix the cause of your pain. In a code base, the cause is usually terrible interfaces and terrible complexity that you want to get rid of because you can no longer maintain that system.”

The Pragmatic Engineer

11,282 Aufrufe • vor 4 Monaten

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...
2:12

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

kwindla

42,246 Aufrufe • vor 1 Jahr

How many AI agents work at your company? We now have over 3,258 agents working alongside 1,300 humans. The crazy part is these agents were created by EVERY EMPLOYEE at our company... sales reps, marketers, customer support, product, eng. Literally EVERYONE. BUT I'm most surprised by the adoption and value that MANAGERS are getting from agents. I used to think that every IC would become a manager of agents. Now I think that managers will very likely manage WAY more agents than their ICs combined. And managers' agents will manage their ICs' agents - overseeing them for human-in-the-loop interactions. When creating agents, we use 100% context from all of your activity, files edited, tasks and projects worked on, hierarchy, skills, and role information. We build a user-based context model to make agents as relatable as possible to the specific human that we're building for. This means they truly understand the nuances of the work and what "great" looks like - because great is very much in the eye of the beholder. Great is by definition, subjective. This is also why the human ENGAGEMENT loops are SO vital to agent value. The iteration AFTER the agent is onboarded is where the MAGIC happens. This is just like a manager managing an IC in real life... you're giving feedback. In this case, though, agents learn INSTANTLY, and they retain the knowledge perfectly and indefinitely. Even though I've been pushing AI for years now to everyone in our company, this was the first time we had truly end-to-end AI adoption and retention. This kind of AI adoption is wild. But the value we're realizing is truly INSANE. Super Agents outnumber our humans nearly 3 to 1. What if you could 3X your workforce overnight? Watch this video to see how 👇
0:59

How many AI agents work at your company? We now have over 3,258 agents working alongside 1,300 humans. The crazy part is these agents were created by EVERY EMPLOYEE at our company... sales reps, marketers, customer support, product, eng. Literally EVERYONE. BUT I'm most surprised by the adoption and value that MANAGERS are getting from agents. I used to think that every IC would become a manager of agents. Now I think that managers will very likely manage WAY more agents than their ICs combined. And managers' agents will manage their ICs' agents - overseeing them for human-in-the-loop interactions. When creating agents, we use 100% context from all of your activity, files edited, tasks and projects worked on, hierarchy, skills, and role information. We build a user-based context model to make agents as relatable as possible to the specific human that we're building for. This means they truly understand the nuances of the work and what "great" looks like - because great is very much in the eye of the beholder. Great is by definition, subjective. This is also why the human ENGAGEMENT loops are SO vital to agent value. The iteration AFTER the agent is onboarded is where the MAGIC happens. This is just like a manager managing an IC in real life... you're giving feedback. In this case, though, agents learn INSTANTLY, and they retain the knowledge perfectly and indefinitely. Even though I've been pushing AI for years now to everyone in our company, this was the first time we had truly end-to-end AI adoption and retention. This kind of AI adoption is wild. But the value we're realizing is truly INSANE. Super Agents outnumber our humans nearly 3 to 1. What if you could 3X your workforce overnight? Watch this video to see how 👇

Zeb Evans

425,244 Aufrufe • vor 7 Monaten

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @pauleveritt@fosstodon.org. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!
2:51

New course: Spec-Driven Development with Coding Agents, built in partnership with JetBrains, and taught by Paul Everitt | @[email protected]. Vibe coding is fast, but often produces code that doesn't match what you asked for. This short course teaches you spec-driven development: write a detailed spec defining what to build, and work with your coding agent to implement it. Many of the best developers already build this way. A spec lets you control large code changes with a few words, preserve context across agent sessions, and stay in control as your project grows in complexity. Skills you'll gain: - Write a detailed specification to define your mission, tech stack, and roadmap, giving your agent the context it needs from the start - Plan, implement, and validate features in iterative loops using a spec as your agent's guide - Apply the same repeatable workflow to both new and legacy codebases - Package your workflow into a portable agent skill that works across agents and IDEs Join and write specs that keep your coding agent on track!

Andrew Ng

464,592 Aufrufe • vor 4 Monaten