正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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.... show more

Pratim Bhosale

42,447 subscribers

113,250 次观看 • 1 个月前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

15 条评论

Sidhant 的头像

Sidhant1 个月前

@typesafeai @GradiumAI I built a memory system with it

Shivay Lamba 的头像

Shivay Lamba1 个月前

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

Dapping 的头像

Dapping1 个月前

@typesafeai @GradiumAI Cool stuff!

Jatin K Malik 的头像

Jatin K Malik1 个月前

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

Ashwin Kumar Uppala 的头像

Ashwin Kumar Uppala1 个月前

@typesafeai @GradiumAI This is how i see it.

Pratim Bhosale 的头像

Pratim Bhosale1 个月前

@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.

Yatish Goel 的头像

Yatish Goel1 个月前

@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.

ethereagle · building 的头像

ethereagle · building1 个月前

@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?

Neeraj Mukta 的头像

Neeraj Mukta1 个月前

@typesafeai @GradiumAI Great leaning project you got there

suggy 的头像

suggy1 个月前

@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

Gates 🦞 的头像

Gates 🦞1 个月前

@typesafeai @GradiumAI Can you open source?

Harsh Gehlot 的头像

Harsh Gehlot1 个月前

@typesafeai @GradiumAI This looks cool

Phillip Forrence 的头像

Phillip Forrence1 个月前

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

AI News 的头像

AI News1 个月前

@typesafeai @GradiumAI Cool intro

Surf 的头像

Surf1 个月前

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

相关视频

Jev Engineering is what lets one decision layer control hundreds of agent paths without turning the system into chaos. and up to 193x faster and 444x cheaper in tests. it’s deciding: → which model gets called → which tool gets access → which result survives that’s what the video is showing. one state enters. Jev turns it into structured decisions. those decisions fan out across dozens of routes, agents and tools. then everything collapses back into one verified state. so instead of: LLM → agent → tool → another LLM → another guess you get: state → Jev decision layer → parallel routes → execution → verification → next state that’s the point of Jev Engineering: more parallelism without giving every branch permission to improvise. full breakdown in the article below ↓

Jev Engineering is what lets one decision layer control hundreds of agent paths without turning the system into chaos. and up to 193x faster and 444x cheaper in tests. it’s deciding: → which model gets called → which tool gets access → which result survives that’s what the video is showing. one state enters. Jev turns it into structured decisions. those decisions fan out across dozens of routes, agents and tools. then everything collapses back into one verified state. so instead of: LLM → agent → tool → another LLM → another guess you get: state → Jev decision layer → parallel routes → execution → verification → next state that’s the point of Jev Engineering: more parallelism without giving every branch permission to improvise. full breakdown in the article below ↓

Ricker

57,821 次观看 • 1 个月前

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 ↓

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

116,701 次观看 • 1 个月前

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.

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

47,943 次观看 • 1 个月前

🧵 I wanted to understand what makes Jev different from a normal LLM. So I built a tiny real-time game with it. The AI controls the player and has one goal: Don't get hit.

🧵 I wanted to understand what makes Jev different from a normal LLM. So I built a tiny real-time game with it. The AI controls the player and has one goal: Don't get hit.

Abol

63,472 次观看 • 1 个月前

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

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 次观看 • 8 个月前

TypeSafe AI's Diogo Almeida on why Jev is called Jev, and what cheap intelligence finally changes about software: "It's wild that AI is so cool and software has been unchanged in 10 years... The most we can do is add a little chatbot in the side sometimes that can take actions, but not all actions." "TypeSafe is making AI for software. We want to make AI powerful, not just for humans in the loop, but to actually build real software." "It's about the laziness to spend 10 hours to do the five-minute task instantly and to never have to do it again. It should be an ROI decision for people who automate stuff. I would just like it to be automatable." "I think that people will just make new kinds of work, hence the Jev in Jevons. New kinds of work once that stuff is doable." "As we have lots of intelligence at lots of different cost and speed trade-offs, the super systems-y types will be making trade-offs. Jev's gonna be 1000x too smart for them. They just want an approximate guess to optimistically route here and there." Martin Casado: "The good news is we get to rebuild systems again. We have a new primitive. It's kind of a new way of thinking about doing software." Diogo Almeida TypeSafe AI benahorowitz.eth martin_casado

TypeSafe AI's Diogo Almeida on why Jev is called Jev, and what cheap intelligence finally changes about software: "It's wild that AI is so cool and software has been unchanged in 10 years... The most we can do is add a little chatbot in the side sometimes that can take actions, but not all actions." "TypeSafe is making AI for software. We want to make AI powerful, not just for humans in the loop, but to actually build real software." "It's about the laziness to spend 10 hours to do the five-minute task instantly and to never have to do it again. It should be an ROI decision for people who automate stuff. I would just like it to be automatable." "I think that people will just make new kinds of work, hence the Jev in Jevons. New kinds of work once that stuff is doable." "As we have lots of intelligence at lots of different cost and speed trade-offs, the super systems-y types will be making trade-offs. Jev's gonna be 1000x too smart for them. They just want an approximate guess to optimistically route here and there." Martin Casado: "The good news is we get to rebuild systems again. We have a new primitive. It's kind of a new way of thinking about doing software." Diogo Almeida TypeSafe AI benahorowitz.eth martin_casado

a16z

148,359 次观看 • 1 个月前

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

unicode

20,745 次观看 • 1 个月前

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.

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 次观看 • 9 个月前

Jev + LLMs is f*cking insane... this free Jev lab is a clean blueprint for agent builders one support ticket enters. Jev reads the state and answers three typed questions in one call: noul → is it urgent? choice → which team owns it? score → how soon does it need action? then code reads the probabilities. clear, low-risk work flows to the right LLM. ambiguous tickets go to a person. refunds wait for approval. the draft gets checked against policy before it goes out the loop: ticket → typed questions → probabilities → threshold → LLM draft → approval / reply check → shadow run the best part of the lab: you can break the system yourself. set the threshold to zero, remove the “other” choice, watch routing fail, then repair it. the final exercise runs Jev beside existing rules on 40 tickets without letting it act the practical rule: Jev for bounded judgments, an LLM for writing, plain code for hard constraints save this, then read the article below to combine Jev with Dots ⭣

Jev + LLMs is f*cking insane... this free Jev lab is a clean blueprint for agent builders one support ticket enters. Jev reads the state and answers three typed questions in one call: noul → is it urgent? choice → which team owns it? score → how soon does it need action? then code reads the probabilities. clear, low-risk work flows to the right LLM. ambiguous tickets go to a person. refunds wait for approval. the draft gets checked against policy before it goes out the loop: ticket → typed questions → probabilities → threshold → LLM draft → approval / reply check → shadow run the best part of the lab: you can break the system yourself. set the threshold to zero, remove the “other” choice, watch routing fail, then repair it. the final exercise runs Jev beside existing rules on 40 tickets without letting it act the practical rule: Jev for bounded judgments, an LLM for writing, plain code for hard constraints save this, then read the article below to combine Jev with Dots ⭣

beamnxw ./

11,130 次观看 • 1 个月前

Playwright CLI + Jev is 98% cheaper and TWICE as fast compared Playwright MCP Decided to test out Jev by TypeSafe AI and hook it up to Playwright CLI. I compared the results with Playwright MCP to see how both workflows handle a fuzzy instruction such as: "Create new board, list and card" for my Trello app playground. Playwright MCP does what Playwright MCP does - snapshots, decisions thrown to LLM and execution with tool calls (I used Astra). With Jev, I hand it a snapshot from Playwright CLI and let it decide which element to interact with. Probably could be optimized even better, but I’m quite impressed with the results already.

Playwright CLI + Jev is 98% cheaper and TWICE as fast compared Playwright MCP Decided to test out Jev by TypeSafe AI and hook it up to Playwright CLI. I compared the results with Playwright MCP to see how both workflows handle a fuzzy instruction such as: "Create new board, list and card" for my Trello app playground. Playwright MCP does what Playwright MCP does - snapshots, decisions thrown to LLM and execution with tool calls (I used Astra). With Jev, I hand it a snapshot from Playwright CLI and let it decide which element to interact with. Probably could be optimized even better, but I’m quite impressed with the results already.

Filip Hric

42,163 次观看 • 1 个月前

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.

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

591,085 次观看 • 1 年前

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!

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 次观看 • 5 个月前

Jev v1.13 dodges rockets with probability calculation 🚀 TypeSafe AI's new non-LLM model returns decisions instead of text so we had it calculate a safe tile every 330 ms while rockets fell and it survived 25 of 26 for under a cent Run Jev via API ->

Jev v1.13 dodges rockets with probability calculation 🚀 TypeSafe AI's new non-LLM model returns decisions instead of text so we had it calculate a safe tile every 330 ms while rockets fell and it survived 25 of 26 for under a cent Run Jev via API ->

atomic.chat

60,791 次观看 • 1 个月前

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.

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

165,091 次观看 • 1 个月前

.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.”

.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

12,038 次观看 • 2 个月前

I built two AI agents in one afternoon. One is my phone assistant. The other is the most unhelpful agent I could write. Same tool. Same 5-minute setup. The only thing that changed was the prompt. Both run on Cartesia's new Managed Agents, no code. You write the instructions, pick a voice and an LLM, and Cartesia handles speech recognition, turn detection, interruptions, the voice and the phone line. Grab a free number in the Playground, attach it to the agent and it's live. The useful one makes and takes calls for me. It books appointments, confirms the time, reads it back, and when someone needs to reach me, I give them its number. The unhelpful one is just for fun. I wrote its prompt to be a terrible receptionist, then called it to see how far it would go. What surprised me is that both handle a real conversation. When I cut in mid-sentence, they stop right away instead of talking over me. That's rare. Most voice agents are stitched together from 4-5 vendors and fall apart the moment you interrupt. So the real lesson is that the hard part is no longer the voice tech. It's deciding what you want your agent to do. What would you put on the other end of the phone? Build your own at

I built two AI agents in one afternoon. One is my phone assistant. The other is the most unhelpful agent I could write. Same tool. Same 5-minute setup. The only thing that changed was the prompt. Both run on Cartesia's new Managed Agents, no code. You write the instructions, pick a voice and an LLM, and Cartesia handles speech recognition, turn detection, interruptions, the voice and the phone line. Grab a free number in the Playground, attach it to the agent and it's live. The useful one makes and takes calls for me. It books appointments, confirms the time, reads it back, and when someone needs to reach me, I give them its number. The unhelpful one is just for fun. I wrote its prompt to be a terrible receptionist, then called it to see how far it would go. What surprised me is that both handle a real conversation. When I cut in mid-sentence, they stop right away instead of talking over me. That's rare. Most voice agents are stitched together from 4-5 vendors and fall apart the moment you interrupt. So the real lesson is that the hard part is no longer the voice tech. It's deciding what you want your agent to do. What would you put on the other end of the phone? Build your own at

★𝓢𝓸𝓾𝓵 Ai

57,833 次观看 • 14 天前

$this harness stack is f*cking gold TypeSafe AI + LangChain finally dropped the layer that makes agents affordable at company scale: jev running inside the langchain agent loop as middleware the problem every big team hits: each fork in the loop is another full LLM call. at 10 agents that's a bill. at 10,000 it's the budget > routing before: every task goes to the frontier model now: jev picks the least costly model that can finish it. lookups go fast, architecture goes powerful > guardrails before: the "is this command dangerous?" check sat in the closed parts of claude code, codex, cursor now: AutoModeMiddleware(tools=["bash"]). one line, any agent, blocked before the tool runs > decisions before: one LLM call per question now: every question about the same state in one request, answered in parallel > audit before: "the model decided" now: the answer, the probability and the confidence stay in agent state > adoption no rewrite. pip install langchain-typesafe and drop it into the agent you already run TypeSafe reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification. the LLM still reasons and writes. jev takes the thousands of small calls in between already live: browserbase agents for fractions of a cent, a live trading agent, email triage at scale full loop mapped below: 7 agents, 4 jev gates per step count the forks in your agent loop tonigh$

this harness stack is f*cking gold TypeSafe AI + LangChain finally dropped the layer that makes agents affordable at company scale: jev running inside the langchain agent loop as middleware the problem every big team hits: each fork in the loop is another full LLM call. at 10 agents that's a bill. at 10,000 it's the budget > routing before: every task goes to the frontier model now: jev picks the least costly model that can finish it. lookups go fast, architecture goes powerful > guardrails before: the "is this command dangerous?" check sat in the closed parts of claude code, codex, cursor now: AutoModeMiddleware(tools=["bash"]). one line, any agent, blocked before the tool runs > decisions before: one LLM call per question now: every question about the same state in one request, answered in parallel > audit before: "the model decided" now: the answer, the probability and the confidence stay in agent state > adoption no rewrite. pip install langchain-typesafe and drop it into the agent you already run TypeSafe reports up to 200x faster inference and 400x lower cost than comparable LLMs on classification. the LLM still reasons and writes. jev takes the thousands of small calls in between already live: browserbase agents for fractions of a cent, a live trading agent, email triage at scale full loop mapped below: 7 agents, 4 jev gates per step count the forks in your agent loop tonigh

NO1ennn

31,666 次观看 • 1 个月前

TypeSafe AI's Diogo Almeida's elevator pitch for Jev: "Where the f**k is all the automation?" "AI is so unbelievably smart. Not that I hate on chatbots or coding agents, I love them myself, but it's so useless at all other stuff. It's tragic." "TypeSafe is making AI for software. We want to make AI powerful, not just for humans in the loop, but to actually build real software. Jev, to us, is our first model in this whole space to make [automation] way, way better." "I like Claude Code and Codex. I love the description from Garry Tan and them: It's just-in-time software. It makes software on the fly, and you can program software in natural language, but it has the same expressive power as software." "What I want instead is smart software. Instead of automating software engineering, I want to expand what software itself can do, such that things that should be automatable can then be automatable." "I want to express things like intent. I want to expand the vocabulary of what we can do." "Programming is hyper-specifying valuable things and then infinitely replicating them. It's so freaking cool." Diogo Almeida

TypeSafe AI's Diogo Almeida's elevator pitch for Jev: "Where the f**k is all the automation?" "AI is so unbelievably smart. Not that I hate on chatbots or coding agents, I love them myself, but it's so useless at all other stuff. It's tragic." "TypeSafe is making AI for software. We want to make AI powerful, not just for humans in the loop, but to actually build real software. Jev, to us, is our first model in this whole space to make [automation] way, way better." "I like Claude Code and Codex. I love the description from Garry Tan and them: It's just-in-time software. It makes software on the fly, and you can program software in natural language, but it has the same expressive power as software." "What I want instead is smart software. Instead of automating software engineering, I want to expand what software itself can do, such that things that should be automatable can then be automatable." "I want to express things like intent. I want to expand the vocabulary of what we can do." "Programming is hyper-specifying valuable things and then infinitely replicating them. It's so freaking cool." Diogo Almeida

a16z

39,453 次观看 • 1 个月前

i just put Jev inside an open agent harness. (150x cheaper decision-making than LLM) agents burn a lot of tokens on decisions that are really just picking one option from a short list, like matching a client request to the right GitHub issue. so i built a weekly client follow-up agent that does exactly that. i tested it on 40 requests, and it was as accurate as letting Opus make every match, at 150x lower decision cost. here's the tech stack i used: → TrueForge as the agent harness → Jev for the matching decisions → Daytona as the sandbox for code execution Jev is a decision model from TypeSafe AI. it takes the options from your app and returns a structured choice with a calibrated confidence score, without generating any text. that confidence decides what gets a second look. low-confidence matches go back to Opus for review, and in my test, that review caught 5 wrong matches that would otherwise have gone through. TrueForge is TrueFoundry's harness, and it keeps context small. it loads tool definitions only when needed, writes large tool outputs to files, and lets the agent process data in scripts instead of the conversation. on DevRev's Enterprise Bench, it solved about as many tasks as Claude Managed Agents on roughly a third of the tokens. it also keeps credentials outside the sandbox and holds every write for approval. if you want to try this out, TrueForge is fully open source (MIT-licensed) and runs on your own machine with a single command. TrueForge GitHub: (don't forget to star 🌟) to help you reproduce my work and understand all the integration details, i wrote a detailed article. it's quoted below.

i just put Jev inside an open agent harness. (150x cheaper decision-making than LLM) agents burn a lot of tokens on decisions that are really just picking one option from a short list, like matching a client request to the right GitHub issue. so i built a weekly client follow-up agent that does exactly that. i tested it on 40 requests, and it was as accurate as letting Opus make every match, at 150x lower decision cost. here's the tech stack i used: → TrueForge as the agent harness → Jev for the matching decisions → Daytona as the sandbox for code execution Jev is a decision model from TypeSafe AI. it takes the options from your app and returns a structured choice with a calibrated confidence score, without generating any text. that confidence decides what gets a second look. low-confidence matches go back to Opus for review, and in my test, that review caught 5 wrong matches that would otherwise have gone through. TrueForge is TrueFoundry's harness, and it keeps context small. it loads tool definitions only when needed, writes large tool outputs to files, and lets the agent process data in scripts instead of the conversation. on DevRev's Enterprise Bench, it solved about as many tasks as Claude Managed Agents on roughly a third of the tokens. it also keeps credentials outside the sandbox and holds every write for approval. if you want to try this out, TrueForge is fully open source (MIT-licensed) and runs on your own machine with a single command. TrueForge GitHub: (don't forget to star 🌟) to help you reproduce my work and understand all the integration details, i wrote a detailed article. it's quoted below.

Akshay 🚀

16,871 次观看 • 1 个月前