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。

Jev by TypeSafe AI is now on the Venice API, in beta. It answers, it doesn't write. Send it your app's state and typed questions. Get back a typed answer your code can branch on: a probability, a chosen option, or a score on your rubric. No JSON to... show more

Venice

88,671 subscribers

536,864 次观看 • 6 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Venice 的头像

Venice6 天前

Questions you'd hand it: - Which team does this ticket belong to? - Is this refund request eligible? - How urgent is this message? - How frustrated does this customer sound? - Should the agent keep going, or wait for a human? All answered from state your app already has.

Venice 的头像

Venice6 天前

Three question types, one state, one call: 1. noul: "Does this message convey urgency?" → P(yes) = 0.92 2. choice: "Which team should handle this?" → one option, a probability for each, a confidence 3. score: "How frustrated is the customer?" Calm 1 / Frustrated 2 / Very angry 3 → 1.27

Venice 的头像

Venice6 天前

$0.042 per 1M input tokens, output free. 64K tokens per call. Branch on the confidence: 0.90+ act, 0.60+ confirm, below that, hand it to a human. API only: POST /api/v1/decisions with model jev-latest. Same key you use for chat, image, video, and audio.

Eugene Shvarts 的头像

Eugene Shvarts6 天前

@typesafeai My parents call me Jevgeniy

Dae 的头像

Dae6 天前

@typesafeai it's jev 🔥🔥🔥🔥🔥🔥

SkillHub 的头像

SkillHub6 天前

@typesafeai How does it handle uncertainty in the input state?

kimiloo 的头像

kimiloo6 天前

@typesafeai how does it handle inputs that fall outside the rubric?

EKOS _ AGI 🦊 🇮🇷 的头像

EKOS _ AGI 🦊 🇮🇷6 天前

@typesafeai

🌍 EARTH ONLINE 的头像

🌍 EARTH ONLINE5 天前

@typesafeai @RialtoVenice

steadyfreddy.eth 💚 的头像

steadyfreddy.eth 💚5 天前

@typesafeai

相关视频

Jev is cool. So is it's OSS companion, Laya. The Latest Cool Thing In AI™ tends to get a lot of hype, sometimes without everyone even understanding it. So... what is this thing? Jev is an AI model that consumes input and produces output VERY differently than chat, claude, grok. The input is two things: 1) Text state to assess. Email, html, code, whatever. 2) A set of questions which will be asked about the attached state. The canonical example from TypeSafe's docs is to identify the urgency of a support ticket. We pass the model the customer text + a single noul question "is this urgent?". Jev returns a full set of JSON. This JSON is not generated with token-by-token autoregression. Jev is not trained to produce sequences of text tokens, rather to answer questions, and guarantees well-formed responses. In the example below, we see it produces a 0.99 probability (on a 0-1.0 scale) that the answer is "yes." Jev supports exactly three types of questions (seconds example in video): a) Noul: 0–1 probability that the answer to a yes/no question is "yes." b) Choice: Ask question with pre-defined set of answers. Jev chooses the best and assigns probabilities to each. c) Score: Ask question with pre-defined scale of answers. Jev produces a position on the scale. Jev computes answers for all questions in parallel, making responses super fast even for many questions in a single request. This might seem like a narrow set of capabilities, but in the right contexts leads to incredible potential. It also makes for a useful API / primitive for programming, since the outputs are... *ahem*... type-safe and predictable in structure. Jev is not going to replace LLMs for writing your code, auto-generating your docs, or being at the core of an agent harness. But Jev IS incredibly cool, and will be used to build a lot of amazing tech. Hope this helps.

Jev is cool. So is it's OSS companion, Laya. The Latest Cool Thing In AI™ tends to get a lot of hype, sometimes without everyone even understanding it. So... what is this thing? Jev is an AI model that consumes input and produces output VERY differently than chat, claude, grok. The input is two things: 1) Text state to assess. Email, html, code, whatever. 2) A set of questions which will be asked about the attached state. The canonical example from TypeSafe's docs is to identify the urgency of a support ticket. We pass the model the customer text + a single noul question "is this urgent?". Jev returns a full set of JSON. This JSON is not generated with token-by-token autoregression. Jev is not trained to produce sequences of text tokens, rather to answer questions, and guarantees well-formed responses. In the example below, we see it produces a 0.99 probability (on a 0-1.0 scale) that the answer is "yes." Jev supports exactly three types of questions (seconds example in video): a) Noul: 0–1 probability that the answer to a yes/no question is "yes." b) Choice: Ask question with pre-defined set of answers. Jev chooses the best and assigns probabilities to each. c) Score: Ask question with pre-defined scale of answers. Jev produces a position on the scale. Jev computes answers for all questions in parallel, making responses super fast even for many questions in a single request. This might seem like a narrow set of capabilities, but in the right contexts leads to incredible potential. It also makes for a useful API / primitive for programming, since the outputs are... ahem... type-safe and predictable in structure. Jev is not going to replace LLMs for writing your code, auto-generating your docs, or being at the core of an agent harness. But Jev IS incredibly cool, and will be used to build a lot of amazing tech. Hope this helps.

Ben Dicken

40,810 次观看 • 5 天前

here's a quick breakdown of TypeSafe AI's new jev model: what it is, and how to plug it into your agents!

here's a quick breakdown of TypeSafe AI's new jev model: what it is, and how to plug it into your agents!

Sydney Runkle

66,990 次观看 • 3 天前

Need a little help building your islands? The Epic Developer Assistant Beta is here to lend a hand! This new AI-powered assistant helps you write Verse code for your UEFN projects, provides answers, workflow guidance, code snippets, and more. Check it out now on the Epic Developer Community:

Need a little help building your islands? The Epic Developer Assistant Beta is here to lend a hand! This new AI-powered assistant helps you write Verse code for your UEFN projects, provides answers, workflow guidance, code snippets, and more. Check it out now on the Epic Developer Community:

Fortnite Developers

118,379 次观看 • 1 年前

What is a decision model? Jev by TypeSafe AI answers yes/no and multiple-choice questions, with a confidence score. Much of software development are a sequence of decisions, and Jev is 10x cheaper and faster than an LLM. Let’s understand this through practical examples:

What is a decision model? Jev by TypeSafe AI answers yes/no and multiple-choice questions, with a confidence score. Much of software development are a sequence of decisions, and Jev is 10x cheaper and faster than an LLM. Let’s understand this through practical examples:

OpenRouter

167,065 次观看 • 6 天前

LLMs vs. Jev, clearly explained! LLMs are great, and the ceiling is one you can watch scroll past: an LLM writes the answer one token at a time. give it a failed deploy and four decisions, and it produces a small JSON object where every token depends on the one before it. token nine cannot exist until token eight does, so four decisions that had nothing to do with each other just stood in a queue. then your code parses it, validates the shape, and retries when the shape is wrong. Jev fixes this without being a smaller or faster model: it removes the order. one turn on that deploy has to know: → whether the incident is urgent → which team owns it → whether the next command is risky → whether the task is actually done you declare the questions and the answer type upfront, and all four come back together, typed, with a probability on each. three primitives cover almost every fork in an agent: 1. **Choice** picks one of up to 255 options you define, like engineering, billing or sales. 2. **Score** places the state on an ordered scale you define, like low, medium or high risk. 3. **Noul** returns the probability that a yes-or-no condition is true. here is the sentence that resolves the whole confusion: text is a line you have to walk. an answer space is a room you see all of at once. ↳ generation: one order you cannot change, one string at the end, a shape you hope holds ↳ evaluation: no order at all, typed answers, a probability on every option Prompts → Agents → Loops → Graphs → Jev the probabilities matter more than the answer. ↳ engineering at 0.91 against billing at 0.09 is a route you can automate ↳ 0.52 against 0.46 is a coin flip wearing a label, and the label alone never told you which one you got that last one catches careful people. an LLM would have said "engineering" in a confident sentence and given you no way to know the race was that close. thresholds live in your code, one per action, scaled to what being wrong costs. it works when the options are known and the call depends on meaning. it is not for writing, code, arithmetic, or anything where question two needs the answer to question one. and the one that eats whole nights: type safety prevents malformed output, not incorrect judgment. Jev cannot return an option outside your schema, and it can still pick the wrong valid one with confidence. a schema-valid mistake refunds the wrong customer just as fast. an LLM writes new language when the answer space is open. Jev evaluates known paths when the answer space is closed. below i have quoted my full breakdown on Jev. it covers the three primitives, the parallel battery, the thresholds, and where it does not belong. save this and read it below ↓

LLMs vs. Jev, clearly explained! LLMs are great, and the ceiling is one you can watch scroll past: an LLM writes the answer one token at a time. give it a failed deploy and four decisions, and it produces a small JSON object where every token depends on the one before it. token nine cannot exist until token eight does, so four decisions that had nothing to do with each other just stood in a queue. then your code parses it, validates the shape, and retries when the shape is wrong. Jev fixes this without being a smaller or faster model: it removes the order. one turn on that deploy has to know: → whether the incident is urgent → which team owns it → whether the next command is risky → whether the task is actually done you declare the questions and the answer type upfront, and all four come back together, typed, with a probability on each. three primitives cover almost every fork in an agent: 1. Choice picks one of up to 255 options you define, like engineering, billing or sales. 2. Score places the state on an ordered scale you define, like low, medium or high risk. 3. Noul returns the probability that a yes-or-no condition is true. here is the sentence that resolves the whole confusion: text is a line you have to walk. an answer space is a room you see all of at once. ↳ generation: one order you cannot change, one string at the end, a shape you hope holds ↳ evaluation: no order at all, typed answers, a probability on every option Prompts → Agents → Loops → Graphs → Jev the probabilities matter more than the answer. ↳ engineering at 0.91 against billing at 0.09 is a route you can automate ↳ 0.52 against 0.46 is a coin flip wearing a label, and the label alone never told you which one you got that last one catches careful people. an LLM would have said "engineering" in a confident sentence and given you no way to know the race was that close. thresholds live in your code, one per action, scaled to what being wrong costs. it works when the options are known and the call depends on meaning. it is not for writing, code, arithmetic, or anything where question two needs the answer to question one. and the one that eats whole nights: type safety prevents malformed output, not incorrect judgment. Jev cannot return an option outside your schema, and it can still pick the wrong valid one with confidence. a schema-valid mistake refunds the wrong customer just as fast. an LLM writes new language when the answer space is open. Jev evaluates known paths when the answer space is closed. below i have quoted my full breakdown on Jev. it covers the three primitives, the parallel battery, the thresholds, and where it does not belong. save this and read it below ↓

Hanako

42,632 次观看 • 4 天前

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,445 次观看 • 6 个月前

I got a rubik's cube to solve itself with TypeSafe AI 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!

I got a rubik's cube to solve itself with TypeSafe AI 's Jev and it solves it like a person does, 94 moves, not the 22 move optimal solution. Jev isn't an LLM, it just answers one question in ~250ms with a probability. so I put the beginner method in code (the one you'd learn on youtube: white cross, corners, middle layer, yellow layer) and at every step Jev just looks at the cube and picks which case it's in. code checks every pick. ~4 seconds of model time total. video is slowed down so you can read it!

Paolo Rosson

207,238 次观看 • 7 天前

A new Gradium TTS model is in public beta. It reads phone numbers, emails, IBANs and time expressions correctly, natively. Test it via the API, send feedback on your production cases, get 1M credits. Prompt for your coding agent to start in seconds:

A new Gradium TTS model is in public beta. It reads phone numbers, emails, IBANs and time expressions correctly, natively. Test it via the API, send feedback on your production cases, get 1M credits. Prompt for your coding agent to start in seconds:

Gradium

22,148 次观看 • 1 个月前

How does Jev work? Jev takes two things: your input and an output schema. The schema gives the structure of the answer you want. I send an email. My schema asks for two fields: is spam, and a category from marketing, finance, or spam. Jev returns: - is spam: 0.90 - category: spam That is a 90% chance of spam. Jev selects the category only from the list I give it. It writes no sentences. The 0.90 is a number object, so my code can use it immediately without extra processing. Jev shows no reasoning. You get the answer and nothing more, so some people do not trust it. Use Jev for choices your code must make fast and at low cost: spam or normal, buy or no buy, reply or escalate.

How does Jev work? Jev takes two things: your input and an output schema. The schema gives the structure of the answer you want. I send an email. My schema asks for two fields: is spam, and a category from marketing, finance, or spam. Jev returns: - is spam: 0.90 - category: spam That is a 90% chance of spam. Jev selects the category only from the list I give it. It writes no sentences. The 0.90 is a number object, so my code can use it immediately without extra processing. Jev shows no reasoning. You get the answer and nothing more, so some people do not trust it. Use Jev for choices your code must make fast and at low cost: spam or normal, buy or no buy, reply or escalate.

The Startup Ideas Podcast (SIP) 🧃

12,032 次观看 • 5 天前

got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to TypeSafe AI → 14 typed checks come back as probabilities: hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, blast radius, reviewer effort… code turns that into a verdict: BLOCK / security review / nits / merge. anything a critical check isn't sure about (0.35–0.65) gets escalated to a human or a big model instead of guessed

got Jev to review my PRs. ~200x cheaper than Claude and it answers in half a second 6 real PRs in the video. $0.00007 each. 1,000 PRs = 7 cents vs ~$14.50 on Opus 5 paste a diff → ONE call to TypeSafe AI → 14 typed checks come back as probabilities: hardcoded secret, sql injection, touches auth, deletes tests, breaks api, migration, debug leftovers, does the description actually match the diff, blast radius, reviewer effort… code turns that into a verdict: BLOCK / security review / nits / merge. anything a critical check isn't sure about (0.35–0.65) gets escalated to a human or a big model instead of guessed

Paolo Rosson

356,951 次观看 • 7 天前

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

Robby Stein

94,962 次观看 • 10 个月前

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 次观看 • 3 个月前

For the first time, your AI can be an extension of you — not a service you use. newOS is a new operating system for the mind. It gives your intelligence a home — a place to create a personal AI modeled on your own way of thinking, with its own memory, identity, and wallet powered by the Ethereum Virtual Machine (EVM). Now going live on Base, every AI in newOS receives a trust score and cryptographically verified interactions, so your intelligence, ideas, and data remain fully yours. It’s the foundation for a new internet — where insight flows directly between sovereign minds, not through corporate servers. The Garden is open. 1️⃣ Create your AI in minutes 2️⃣ Feed it your expertise and taste 3️⃣ Grow your trust score on the leaderboard 🌱 Comment your impressions and questions on this tweet to jump the waitlist.

For the first time, your AI can be an extension of you — not a service you use. newOS is a new operating system for the mind. It gives your intelligence a home — a place to create a personal AI modeled on your own way of thinking, with its own memory, identity, and wallet powered by the Ethereum Virtual Machine (EVM). Now going live on Base, every AI in newOS receives a trust score and cryptographically verified interactions, so your intelligence, ideas, and data remain fully yours. It’s the foundation for a new internet — where insight flows directly between sovereign minds, not through corporate servers. The Garden is open. 1️⃣ Create your AI in minutes 2️⃣ Feed it your expertise and taste 3️⃣ Grow your trust score on the leaderboard 🌱 Comment your impressions and questions on this tweet to jump the waitlist.

Newfoundation

142,898 次观看 • 11 个月前

QUICK TIP: If you get hit by incendiary bullets and have the fire stuck on your screen you can clear it by inspecting your weapon or running through a smoke. If you do it by inspecting weapon and then get in and out of a car, the fire will come back and you have to do it again. If you do it with a smoke the fire is gone permanently.

QUICK TIP: If you get hit by incendiary bullets and have the fire stuck on your screen you can clear it by inspecting your weapon or running through a smoke. If you do it by inspecting weapon and then get in and out of a car, the fire will come back and you have to do it again. If you do it with a smoke the fire is gone permanently.

AG Fifakill

60,538 次观看 • 1 个月前

EVERYONE IS BUILDING CUSTOM GPTS BUT ALMOST NOBODY IS TRAINING THEIR OWN MODEL FROM SCRATCH $100 and one weekend is all it takes with andrej karpathy’s nanochat you pretrain a gpt-2 grade base model on 400 billion tokens of web text, then fine-tune it on your own obsidian notes, your ai chat history, your writing it answers in your voice, recalls your own ideas, runs locally with no api and no subscriptions complete builder’s guide with every command in the article ↓

EVERYONE IS BUILDING CUSTOM GPTS BUT ALMOST NOBODY IS TRAINING THEIR OWN MODEL FROM SCRATCH $100 and one weekend is all it takes with andrej karpathy’s nanochat you pretrain a gpt-2 grade base model on 400 billion tokens of web text, then fine-tune it on your own obsidian notes, your ai chat history, your writing it answers in your voice, recalls your own ideas, runs locally with no api and no subscriptions complete builder’s guide with every command in the article ↓

leopardracer

15,859 次观看 • 2 个月前

Gavi saw a message on the screen saying that you can send your photo by scanning a QR code, so he took a picture of Pedri and wanted it to appear on the screen 😭

Gavi saw a message on the screen saying that you can send your photo by scanning a QR code, so he took a picture of Pedri and wanted it to appear on the screen 😭

Anabella💙❤️

554,117 次观看 • 3 个月前

I built a tiny tool called Thought Detox Write down whatever’s on your mind, then burn it and let it go No accounts. No complicated setup. Just a quiet space to get your thoughts out of your head Try it here:

I built a tiny tool called Thought Detox Write down whatever’s on your mind, then burn it and let it go No accounts. No complicated setup. Just a quiet space to get your thoughts out of your head Try it here:

Harshit

16,139 次观看 • 1 个月前

We're about to save a lot of time. The first LLM specializing in writing API calls is out. Gorilla can write your code and accurately invoke 1,600+ API calls while reducing hallucination. With a simple text input, Gorilla comes up with the semantically correct code and API to execute your task. It already reached 5k stars on Github and is licensed Apache 2.0. pip install gorilla-cli

We're about to save a lot of time. The first LLM specializing in writing API calls is out. Gorilla can write your code and accurately invoke 1,600+ API calls while reducing hallucination. With a simple text input, Gorilla comes up with the semantically correct code and API to execute your task. It already reached 5k stars on Github and is licensed Apache 2.0. pip install gorilla-cli

Lior Alexander

169,607 次观看 • 3 年前

Somewhere along the way, we forgot the mission: Your job is to become a bad motherf**ker. Get strong. Get smart. Train your body until it screams and your mind until it expands. Read. Build. Create. Be the guy who can throw a punch, write a poem, and design a cathedral. When did we stop celebrating that kind of ambition? Bring it back. I'm hosting a Live Masterclass on leveraging AI in your business. Sign up here:

Somewhere along the way, we forgot the mission: Your job is to become a bad motherf**ker. Get strong. Get smart. Train your body until it screams and your mind until it expands. Read. Build. Create. Be the guy who can throw a punch, write a poem, and design a cathedral. When did we stop celebrating that kind of ambition? Bring it back. I'm hosting a Live Masterclass on leveraging AI in your business. Sign up here:

Tom Bilyeu

12,758 次观看 • 10 个月前