Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Played around with TypeSafe AI Jev today, mostly to understand what it does for tool calling. Instead of an LLM deciding what to do, I substituted that part with Jev. My learning is that we will be able to make the agent act before the user finishes the sentence....

BhosalePratim's profile picture

Pratim Bhosale

42,486 subscribers

110,761 Aufrufe • vor 2 Tagen •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

15 Kommentare

Profilbild von Sidhant
Sidhantvor 2 Tagen

@typesafeai @GradiumAI I built a memory system with it

Profilbild von Shivay Lamba
Shivay Lambavor 2 Tagen

@typesafeai @GradiumAI loved the explanation, and this unlocks so many use-cases previously not possible with LLM based systems

Profilbild von Dapping
Dappingvor 2 Tagen

@typesafeai @GradiumAI Cool stuff!

Profilbild von Jatin K Malik
Jatin K Malikvor 2 Tagen

@typesafeai @GradiumAI It's crazy this is going to expand into endless use cases i can think from top of my head

Profilbild von Ashwin Kumar Uppala
Ashwin Kumar Uppalavor 2 Tagen

@typesafeai @GradiumAI This is how i see it.

Profilbild von Pratim Bhosale
Pratim Bhosalevor 2 Tagen

@typesafeai @GradiumAI That’s what I meant to build as well😂. Codex’s UI skills went only so far. I'm integrating the blender MCP now.

Profilbild von Yatish Goel
Yatish Goelvor 2 Tagen

@typesafeai @GradiumAI 'Cancel my booking... actually, just check the cancellation fee' would be a useful test. I'd start the lookup on partial speech, but wait before doing anything that changes the booking.

Profilbild von ethereagle · building
ethereagle · buildingvor 2 Tagen

@typesafeai @GradiumAI acting on a prefix only works if the wrong tool is cheap to undo. for voice, do you wait for a Jev confidence cutoff, or fire as soon as one tool scores highest?

Profilbild von Neeraj Mukta
Neeraj Muktavor 2 Tagen

@typesafeai @GradiumAI Great leaning project you got there

Profilbild von suggy
suggyvor 2 Tagen

@typesafeai @GradiumAI acting before the user finishes is powerful and slightly terrifying I'd want a confidence threshold + an easy undo path before letting prediction turn into side effects

Profilbild von Gates 🦞
Gates 🦞vor 2 Tagen

@typesafeai @GradiumAI Can you open source?

Profilbild von Harsh Gehlot
Harsh Gehlotvor 2 Tagen

@typesafeai @GradiumAI This looks cool

Profilbild von Phillip Forrence
Phillip Forrencevor 2 Tagen

@typesafeai @GradiumAI Someone put a ring on her finger!

Profilbild von AI News
AI Newsvor 2 Tagen

@typesafeai @GradiumAI Cool intro

Profilbild von Surf
Surfvor 2 Tagen

@typesafeai @GradiumAI Would be nice to be able to see the code on a github repo

Ähnliche Videos

Jev Engineering is the layer most agent stacks are still missing. state → decision → action → verification → next state up to 193x faster and 444x cheaper in our tests. everyone is optimizing the model. Jev Engineering optimizes what happens between model calls. every agent eventually hits the same fork: state → multiple possible actions → one route has to win instead of sending every decision back to an expensive LLM call, Jev turns that into a dedicated layer: so the loop becomes: LLM → reason Jev → decide tools / agents → execute state → update Jev → decide again once decisions become their own engineering layer, you can benchmark, batch and verify them separately. full blueprint in article ↓
0:29

Jev Engineering is the layer most agent stacks are still missing. state → decision → action → verification → next state up to 193x faster and 444x cheaper in our tests. everyone is optimizing the model. Jev Engineering optimizes what happens between model calls. every agent eventually hits the same fork: state → multiple possible actions → one route has to win instead of sending every decision back to an expensive LLM call, Jev turns that into a dedicated layer: so the loop becomes: LLM → reason Jev → decide tools / agents → execute state → update Jev → decide again once decisions become their own engineering layer, you can benchmark, batch and verify them separately. full blueprint in article ↓

Ricker

83,098 Aufrufe • vor 1 Tag

Wow, TypeSafe AI Jev is a game changer for voice-driven UI. Responsiveness really matters for an experience to 'feel' right, and this certainly does the job! Latency here is not optimal given I'm in London and calling out to us-west. But still, super snappy. In this video, Jamcat is using Pipecat to orchestrate a real-time handover between a command agent (Jev) that drives the UI, and voice agent (PhoneLLM) for handling generations and (not in the video) discussing ideas and session setup with the user.
1:39

Wow, TypeSafe AI Jev is a game changer for voice-driven UI. Responsiveness really matters for an experience to 'feel' right, and this certainly does the job! Latency here is not optimal given I'm in London and calling out to us-west. But still, super snappy. In this video, Jamcat is using Pipecat to orchestrate a real-time handover between a command agent (Jev) that drives the UI, and voice agent (PhoneLLM) for handling generations and (not in the video) discussing ideas and session setup with the user.

Jon Taylor

43,880 Aufrufe • vor 3 Tagen

Most traders get trapped for years, thinking that trading is about predicting what the market will do next, instead of assessing what the market is doing now. I hope this video helps many of you understand what the difference is, and how you can apply that concept to your own trading. $BTC #Bitcoin
40:31

Most traders get trapped for years, thinking that trading is about predicting what the market will do next, instead of assessing what the market is doing now. I hope this video helps many of you understand what the difference is, and how you can apply that concept to your own trading. $BTC #Bitcoin

Lucky Chart Ape

18,466 Aufrufe • vor 6 Monaten

I built a tool to imagine how AI can help us create better, more transparent research. Instead of only seeing the tiny number of analyses the author chooses to ossify in a static pdf, imagine being able to talk to the papers you read and ask for different analyses. That's what I built. This early prototype uses our vote-by-mail extension. You get to see the initial analyses we thought made sense, but you can ask the LLM to show you way more! e.g., "what would the results look like if we excluded Utah" or "what would the results look like if we excluded Washington and used linear trends" etc. With research agents like Claude code, researchers are going to be able to automatically search across millions of potential analyses. Our current paradigm is not equipped to transmit this complexity effectively or make sure we don't end up with all p-hacked results. My lab and I are thinking about how we can transform the way we do and disseminate research to adjust for this new world. This visualizer is the first of what will hopefully be a wide range of ideas. Big props to Janet Malzahn for suggesting this one. Check out the tool at the link below.
0:26

I built a tool to imagine how AI can help us create better, more transparent research. Instead of only seeing the tiny number of analyses the author chooses to ossify in a static pdf, imagine being able to talk to the papers you read and ask for different analyses. That's what I built. This early prototype uses our vote-by-mail extension. You get to see the initial analyses we thought made sense, but you can ask the LLM to show you way more! e.g., "what would the results look like if we excluded Utah" or "what would the results look like if we excluded Washington and used linear trends" etc. With research agents like Claude code, researchers are going to be able to automatically search across millions of potential analyses. Our current paradigm is not equipped to transmit this complexity effectively or make sure we don't end up with all p-hacked results. My lab and I are thinking about how we can transform the way we do and disseminate research to adjust for this new world. This visualizer is the first of what will hopefully be a wide range of ideas. Big props to Janet Malzahn for suggesting this one. Check out the tool at the link below.

Andy Hall

70,844 Aufrufe • vor 8 Monaten

Aravind Srinivas's hypothesis on how advertising works with AI agents is quite interesting. Aravind explains, Instead of showing ads to humans directly, advertisements would be targeted at AI agents that work on users' behalf. Users never see ads, they simply tell their AI agents what they need for eg if he gave, "I'm going to go to Rambagh for two nights, plan my schedule, do my bookings" In the backend, Multiple vendors compete for the agent's attention & companies bid for the agent's consideration. So everything happens at the AI level. Agents can also use more compute power to analyse offer to find out advertising attempts & make decisions based on user preferences. Also users can instruct their agents to ignore certain brands , this will remain confidential to between the agent & the user. This creates new revenue streams for AI companies & gives a better user experience.
1:39

Aravind Srinivas's hypothesis on how advertising works with AI agents is quite interesting. Aravind explains, Instead of showing ads to humans directly, advertisements would be targeted at AI agents that work on users' behalf. Users never see ads, they simply tell their AI agents what they need for eg if he gave, "I'm going to go to Rambagh for two nights, plan my schedule, do my bookings" In the backend, Multiple vendors compete for the agent's attention & companies bid for the agent's consideration. So everything happens at the AI level. Agents can also use more compute power to analyse offer to find out advertising attempts & make decisions based on user preferences. Also users can instruct their agents to ignore certain brands , this will remain confidential to between the agent & the user. This creates new revenue streams for AI companies & gives a better user experience.

Aish

590,837 Aufrufe • vor 1 Jahr

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

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on The Startup Ideas Podcast (SIP) 🧃 (thanks to vogel for coming on and spilling the sauce today) Watch: Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.
28:24

Jev is HERE and this is the CLEAREST explanation of what it is and what NEW businesses it unlocks. (and at the end I'll tell you how to get Jev even if you're on the waitlist) WHAT IT IS You know how you open your inbox and have to decide what's junk, what needs a reply, and what can wait? Jev does that part. It looks at each thing and says "this is junk, I'm 94% sure." It doesn't write anything back to you. It just sorts. 1,700 emails for 18 cents, instantly. That sounds kinda trivial but the important part WHAT IT UNLOCKS My explanation of Jev sounds small until you realize HOW MANY jobs are exactly this. Someone reading a stack of applications. Someone deciding which support ticket goes to which team. Someone looking at inbound and deciding who's worth calling back. A few ideas on what it unlocks: 1/ Instant quotes that are actually instant. Every quote form on the internet says "we'll email you by end of day." Build the version that answers in under a second, for roofers, movers, insurance, legal intake. 2/ Lead scoring as a product. Every agency and service business has a contact form full of junk. Score every submission and send the real ones straight to the owner's phone. 3/ Support triage for companies with no support team. The ticket gets classified and routed before anyone opens it. 4/ Clipping tools. Pass in a transcript, get the best moments scored in three seconds. Every clipping product just got a cheaper engine. 5/ Application piles. Grants, permits, insurance claims, job apps, loan docs. Someone reads that stack one item at a time today. 6/ Marketplace matching. Someone types what they need and gets matched to the right local business instantly instead of waiting for callbacks. 7/ Browser agents that actually move FAST. That makes bulk browser work practical: pulling quotes from five carriers, filing the same form for 200 clients, checking supplier inventory in real time etc. TLDR; find an expensive queue and put Jev at the front of it. HOW TO GET IT I didn't realize you can skip the waitlist because Jev is live on the Vercel AI Gateway right now, so you can start calling it today. In this episode, we share how. Episode now live on The Startup Ideas Podcast (SIP) 🧃 (thanks to vogel for coming on and spilling the sauce today) Watch: Jev is a big deal because this is a whole new way to do AI Really cool Happy Jev day.

GREG ISENBERG

148,535 Aufrufe • vor 2 Tagen

.Mati Staniszewski on The Future of Human-AI Interaction: “Voice will 100% will be one of the biggest ways you interact with AI.” “AI will be able to connect the IQ plus the EQ part of it. It will be able to emotionally understand you. It will know how you're feeling and can adjust based on that. It can pause and can think and can reinsert itself into the conversation.” “Voice is the most primal way we communicate and now we can bring technology back on our terms.” “So 12 months from now I think AI will be able to understand us in an incredibly better way —both our knowledge and emotional part. And deliver similar conversation to the one we are having now.”
1:35

.Mati Staniszewski on The Future of Human-AI Interaction: “Voice will 100% will be one of the biggest ways you interact with AI.” “AI will be able to connect the IQ plus the EQ part of it. It will be able to emotionally understand you. It will know how you're feeling and can adjust based on that. It can pause and can think and can reinsert itself into the conversation.” “Voice is the most primal way we communicate and now we can bring technology back on our terms.” “So 12 months from now I think AI will be able to understand us in an incredibly better way —both our knowledge and emotional part. And deliver similar conversation to the one we are having now.”

David Senra

11,582 Aufrufe • vor 11 Tagen

Notice how off the bat he completely flipped it back onto her? Instead of actually answering the question. And then he proceeds to bulldoze her with bs that has nothing to do with the fact that men - can never, ever understand what it is to be a woman. His experience of being a man pretending to be a woman is irrelevant to what women are. We already exist. We aren’t an idea.
0:48

Notice how off the bat he completely flipped it back onto her? Instead of actually answering the question. And then he proceeds to bulldoze her with bs that has nothing to do with the fact that men - can never, ever understand what it is to be a woman. His experience of being a man pretending to be a woman is irrelevant to what women are. We already exist. We aren’t an idea.

Stellar_Fox

17,054 Aufrufe • vor 4 Monaten

Zelensky says he is ready for direct talks with Putin to end the war "I am ready for direct negotiations with Putin to end this war, instead of waiting until all the conflicts in the world are resolved, and only then will it be Ukraine's turn."
1:42

Zelensky says he is ready for direct talks with Putin to end the war "I am ready for direct negotiations with Putin to end this war, instead of waiting until all the conflicts in the world are resolved, and only then will it be Ukraine's turn."

Visegrád 24

97,001 Aufrufe • vor 3 Monaten

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 a bunch of things I’m currently obsessed with, in an application of non-trivial size, that felt both new and old at the same time. So … a retro-style space trading game built entirely around interacting with and managing multiple LLMs. Factorio, but instead of clicking, you cajole your ship AI into tasking other AIs to do things for you. Some of the things we’ve been thinking about as we hack on Gradient Bang: - Sub-agent orchestration - Partial context sharing between multiple LLM inference loops - Managing very long contexts, and episodic memory across user sessions - World events and large volumes of structured data input as part of human/agent conversations - Dynamic user interfaces, driven/created on the fly by LLMs - And, of course, voice as primary input If you’ve been building coding harnesses, or writing Open Claw agents, or doing pretty much anything that pushes the boundaries of AI-native development these days, you’re probably thinking about these things too! This is all built with Pipecat AI, the back end is Supabase, the React front end is deployed to Vercel, and all the code is open source.
1:03

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 a bunch of things I’m currently obsessed with, in an application of non-trivial size, that felt both new and old at the same time. So … a retro-style space trading game built entirely around interacting with and managing multiple LLMs. Factorio, but instead of clicking, you cajole your ship AI into tasking other AIs to do things for you. Some of the things we’ve been thinking about as we hack on Gradient Bang: - Sub-agent orchestration - Partial context sharing between multiple LLM inference loops - Managing very long contexts, and episodic memory across user sessions - World events and large volumes of structured data input as part of human/agent conversations - Dynamic user interfaces, driven/created on the fly by LLMs - And, of course, voice as primary input If you’ve been building coding harnesses, or writing Open Claw agents, or doing pretty much anything that pushes the boundaries of AI-native development these days, you’re probably thinking about these things too! This is all built with Pipecat AI, the back end is Supabase, the React front end is deployed to Vercel, and all the code is open source.

kwindla

456,432 Aufrufe • vor 5 Monaten

A look at the future: chatting with my robot via Discord to ask it to find something in my house. - Use an LLM agent (Qwen, OpenAI's GPT-4o, whatever) to understand what the user wants and generate a task plan - Use open-vocabulary 3d scene representations to build up a representation of the world that we can use to find objects - Interface with social media chat programs to do things like send a picture of what the robot sees
0:53

A look at the future: chatting with my robot via Discord to ask it to find something in my house. - Use an LLM agent (Qwen, OpenAI's GPT-4o, whatever) to understand what the user wants and generate a task plan - Use open-vocabulary 3d scene representations to build up a representation of the world that we can use to find objects - Interface with social media chat programs to do things like send a picture of what the robot sees

Chris Paxton

40,472 Aufrufe • vor 1 Jahr

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!
2:06

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,131 Aufrufe • vor 2 Jahren

"This is the best way of going back into Indian films... work with SS.Rajamouli, his vision is so far beyond limited imagination that just to be able to see what he's thinking for the story is great... my part is amazing" Priyanka Chopra about Varanasi #MaheshBabu
1:48

"This is the best way of going back into Indian films... work with SS.Rajamouli, his vision is so far beyond limited imagination that just to be able to see what he's thinking for the story is great... my part is amazing" Priyanka Chopra about Varanasi #MaheshBabu

NP LEGΛCY 🇨🇴🫰🏽

37,025 Aufrufe • vor 6 Monaten

"We've move to Resend for so much of our marketing communications. Why? Our AI Agents can talk to it. So easily. And that means we can vibe with it. We can get it to do almost anything we want it to do. That's the new bar today." The latest Agents #002 is out!
1:41

"We've move to Resend for so much of our marketing communications. Why? Our AI Agents can talk to it. So easily. And that means we can vibe with it. We can get it to do almost anything we want it to do. That's the new bar today." The latest Agents #002 is out!

Jason ✨👾SaaStr.Ai✨ Lemkin

18,823 Aufrufe • vor 4 Monaten

Introducing the Papers with Code MCP server! To celebrate its release, I've asked Claude Code to research the architecture of Jev by TypeSafe AI using the `search_papers` tool. Here's what it came up with: "If Jev is architecturally anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far past the ~150M-param range those papers operate in — "neither small nor an LLM" fits that. The 40–200× speedup is consistent with removing autoregression, not with any exotic mechanism."
1:16

Introducing the Papers with Code MCP server! To celebrate its release, I've asked Claude Code to research the architecture of Jev by TypeSafe AI using the `search_papers` tool. Here's what it came up with: "If Jev is architecturally anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far past the ~150M-param range those papers operate in — "neither small nor an LLM" fits that. The 40–200× speedup is consistent with removing autoregression, not with any exotic mechanism."

Niels Rogge

19,452 Aufrufe • vor 3 Tagen