Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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_hq's profile picture

atomic.chat

17,334 subscribers

60,791 Aufrufe • vor 18 Tagen •via X (Twitter)

Wissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

4 Kommentare

Profilbild von Julian Pscheid
Julian Pscheidvor 18 Tagen

@typesafeai I wish it was actually running local. Seems like other labs should be able to replicate this pretty quickly.

Profilbild von BasedAntiLeft
BasedAntiLeftvor 18 Tagen

@typesafeai Jev just solved the nuclear threat

Profilbild von Daniel Yurkin
Daniel Yurkinvor 18 Tagen

@typesafeai 🚀

Profilbild von Berelz
Berelzvor 18 Tagen

@typesafeai All i see is new drone warfare capabilities

Ähnliche Videos

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!
0:34

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

207,767 Aufrufe • vor 19 Tagen

I got early access to TypeSafe AI's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" moment
0:28

I got early access to TypeSafe AI's new Jev model and built a demo of it playing tetris The generation speed is so fast that it's pushing blocks down This feels like another "this changes everything" moment

Marcus Lowe

79,908 Aufrufe • vor 19 Tagen

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. So far, we've used different LLM combinations (non-thinking + thinking ) plus state machine setups to get the right experience for the end user. TLDR is to understand more about how voice agents can run decisions on partials instead of waiting for the end of the turn, with lower costs.
1:10

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. So far, we've used different LLM combinations (non-thinking + thinking ) plus state machine setups to get the right experience for the end user. TLDR is to understand more about how voice agents can run decisions on partials instead of waiting for the end of the turn, with lower costs.

Pratim Bhosale

112,821 Aufrufe • vor 17 Tagen

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build
0:22

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

NO1ennn

18,445 Aufrufe • vor 7 Tagen

this is f*cking gold 12 open-source repos that plug Jev into real AI work, 550.7k stars combined Jev decides, your LLM writes. these repos are where that split already runs: agents > browser-use/jev-ultrafast (~20.3k): Jev picks the next action + DOM element, a small LLM only types. Zürich to London flights in ~7s > awlevin/typesafe-computer-use (~978): macOS computer use, OCR reads the screen, Jev picks the next click local decision models > jaredpalmer/kev (~7.1k): Jev-like models on Qwen, same /v1/systemone wire format > mizorewww/laya-mlx (~6.4k): Laya, the main open Jev-style engine, running on Apple silicon > TheoLeeCJ/SemIf-OpenJev (~4.3k): local semantic ifs from frozen open models, not a TypeSafe project > contrastive-lm/clm (~1.3k): open System One model with a Choice / Noul / Score API > vinnylarouge/jevlike (~1.3k): community trainer and tooling for your own Jev-like model context + skills > tamaratran/fast-jev-compaction (~6.9k): Claude Code plugin, Jev keeps, drops or truncates tool results instead of summarizing context > typesafe-ai/skills (~2.2k): official TypeSafe skill for Claude Code and Codex trading > jarrodwatts/jev-trader (~2.4k): one Jev buy/sell decision per Monad block catalogs > yibie/awesome-jev (~1.7k): the biggest map of Jev projects and discussions > Anil-matcha/awesome-jev-by-typesafe (~851): use cases, patterns and starter code start with jev-ultrafast
0:22

this is f*cking gold 12 open-source repos that plug Jev into real AI work, 550.7k stars combined Jev decides, your LLM writes. these repos are where that split already runs: agents > browser-use/jev-ultrafast (~20.3k): Jev picks the next action + DOM element, a small LLM only types. Zürich to London flights in ~7s > awlevin/typesafe-computer-use (~978): macOS computer use, OCR reads the screen, Jev picks the next click local decision models > jaredpalmer/kev (~7.1k): Jev-like models on Qwen, same /v1/systemone wire format > mizorewww/laya-mlx (~6.4k): Laya, the main open Jev-style engine, running on Apple silicon > TheoLeeCJ/SemIf-OpenJev (~4.3k): local semantic ifs from frozen open models, not a TypeSafe project > contrastive-lm/clm (~1.3k): open System One model with a Choice / Noul / Score API > vinnylarouge/jevlike (~1.3k): community trainer and tooling for your own Jev-like model context + skills > tamaratran/fast-jev-compaction (~6.9k): Claude Code plugin, Jev keeps, drops or truncates tool results instead of summarizing context > typesafe-ai/skills (~2.2k): official TypeSafe skill for Claude Code and Codex trading > jarrodwatts/jev-trader (~2.4k): one Jev buy/sell decision per Monad block catalogs > yibie/awesome-jev (~1.7k): the biggest map of Jev projects and discussions > Anil-matcha/awesome-jev-by-typesafe (~851): use cases, patterns and starter code start with jev-ultrafast

NO1ennn

41,408 Aufrufe • vor 9 Tagen

Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is one API call. Jev V13 vs Fable 5.1: • fable outplayed it. by move 29 it was +16 in material and even promoted a second queen • but it kept burning 6-15 seconds per move on analysis. jev answered in ~2.6s • so fable didn't have enough time and lost Jev V13 vs Astra: • astra didn't bother winning on material. it mated jev in 18 moves. Qe1#, with 2:27 to spare
1:39

Jev VS Fable 5.1 VS GPT-6 Astra: chess typesafe's new Jev V13 isn't an LLM. it doesn't chat, doesn't explain, doesn't write code — it only makes decisions. so we made it play blitz against frontier LLMs. the test: 5+0 blitz. every move is one API call. Jev V13 vs Fable 5.1: • fable outplayed it. by move 29 it was +16 in material and even promoted a second queen • but it kept burning 6-15 seconds per move on analysis. jev answered in ~2.6s • so fable didn't have enough time and lost Jev V13 vs Astra: • astra didn't bother winning on material. it mated jev in 18 moves. Qe1#, with 2:27 to spare

AI/ML API

564,226 Aufrufe • vor 19 Tagen

TypeSafe's new model Jev is everywhere this week, and it doesn't even generate text. It returns decisions: typed scores your code uses directly, in a single pass. We put it to work in a real-time chat moderator, scoring toxicity, frustration, and spam in 300 to 400ms. Then we deployed the Node.js backend on Cloudways Velocity. It runs as a persistent process, so no serverless cold start eats the speed Jev just gave you.
0:47

TypeSafe's new model Jev is everywhere this week, and it doesn't even generate text. It returns decisions: typed scores your code uses directly, in a single pass. We put it to work in a real-time chat moderator, scoring toxicity, frustration, and spam in 300 to 400ms. Then we deployed the Node.js backend on Cloudways Velocity. It runs as a persistent process, so no serverless cold start eats the speed Jev just gave you.

Cloudways

26,136 Aufrufe • vor 11 Tagen

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:32

Jev has been exploding in popularity recently. If you already have access to the Jev API but aren't sure how to start experimenting with it, just copy this checklist: 1. jev-ultrafast Browser Use's fastest agent. Jev decides the next action and which element to click, and a language model is only called when text has to be typed. 2. typesafe-mario Jev plays Super Mario Bros. from structured emulator state, choosing every action from features pulled out of the game. 3. jev-plays-pokemon Reads Pokémon Red's game state as text, answers typed questions each turn, and lets plain code turn the answers into moves. 4. jev-drone A camera-only autonomous drone in MuJoCo with a Jev judgment model sitting in the control loop at 2.5 Hz. 5. robo-harness A real SO-101 robot arm workbench where Jev picks bounded joint steps from typed candidate actions under a spend budget. 6. fast-jev-compaction Claude Code plugin that replaces the compaction summary with Jev decisions, scoring every tool call for whether it is still needed. 7. jev-claude Routes Claude Code's own judgment calls through Jev: typed choices with probabilities at plan approval, on questions, and before risky commands. 8. is-malicious Supply-chain check before you run anything: Jev Noul checks over source and build files, returning the implicated files and lines. 9. sqlite-jev Jev inside SQL. Noul, Choice and Score judgments exposed as SQLite functions, with confidence on every row. 10. jevinci Paints images by having Jev predict every pixel's colour in parallel, with confidence deciding how wide each stroke is drawn. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

Hanako

29,894 Aufrufe • vor 11 Tagen

this is pure f*cking treasure Engineer at TypeSafeAI just mapped 389 public Jev builds in one list: skills, MCP servers, SDKs, agents, benchmarks and guides ROUTING > jev-router sends every Claude Code task to the cheapest model that can do it > Switchboard picks the model and reasoning effort per task, then keeps it stable so the prompt cache survives > jev-oncall triages alerts: 418 ms p50, $0.04 per 1,000 alerts GUARDRAILS > jev-axi gates shell commands for Claude Code and Codex, 44/44 on its labeled set > hermes-jev-approvals: 8.7x faster approvals, 4.4x fewer prompts to the user > Sniff Test lints AI slop out of your writing at 182 ms a paragraph AGENTS > Jev Ultrafast: Jev picks every click, a small LLM only types > fast-jev-compaction scores your context instead of summarizing it > jev-browser-use reports 5 to 10x faster browser runs inside Codex SEARCH & RAG > jev-retrieval placed 2nd of 90 models on a reranking leaderboard > jevsearch: 83% Hit@1 against 41% for keyword search alone SDKs & MCP > clients for Swift, Go, Rust, Kotlin, Ruby, Elixir, .NET, Laravel and Spring > MCP servers for Claude Code, Cursor and Codex > Jev inside SQLite, DuckDB and Postgres, straight from SQL EVALS > pytest-jev checks LLM replies in 5.3 s where Claude took 27.1 s > a medical hallucination check at 92.9% accuracy, 204 ms, $0.03 per 1,000 OPEN MODELS > Laya answers in one ~35 ms forward pass > kev trains and runs on a MacBook GAMES, ROBOTS, TRADING > Jev plays Mario, Pokemon and chess > it drives a robot arm and a drone > it trades on Monad with 81 ms decisions 389 builds. one decision layer. go steal the ones you need
0:24

this is pure f*cking treasure Engineer at TypeSafeAI just mapped 389 public Jev builds in one list: skills, MCP servers, SDKs, agents, benchmarks and guides ROUTING > jev-router sends every Claude Code task to the cheapest model that can do it > Switchboard picks the model and reasoning effort per task, then keeps it stable so the prompt cache survives > jev-oncall triages alerts: 418 ms p50, $0.04 per 1,000 alerts GUARDRAILS > jev-axi gates shell commands for Claude Code and Codex, 44/44 on its labeled set > hermes-jev-approvals: 8.7x faster approvals, 4.4x fewer prompts to the user > Sniff Test lints AI slop out of your writing at 182 ms a paragraph AGENTS > Jev Ultrafast: Jev picks every click, a small LLM only types > fast-jev-compaction scores your context instead of summarizing it > jev-browser-use reports 5 to 10x faster browser runs inside Codex SEARCH & RAG > jev-retrieval placed 2nd of 90 models on a reranking leaderboard > jevsearch: 83% Hit@1 against 41% for keyword search alone SDKs & MCP > clients for Swift, Go, Rust, Kotlin, Ruby, Elixir, .NET, Laravel and Spring > MCP servers for Claude Code, Cursor and Codex > Jev inside SQLite, DuckDB and Postgres, straight from SQL EVALS > pytest-jev checks LLM replies in 5.3 s where Claude took 27.1 s > a medical hallucination check at 92.9% accuracy, 204 ms, $0.03 per 1,000 OPEN MODELS > Laya answers in one ~35 ms forward pass > kev trains and runs on a MacBook GAMES, ROBOTS, TRADING > Jev plays Mario, Pokemon and chess > it drives a robot arm and a drone > it trades on Monad with 81 ms decisions 389 builds. one decision layer. go steal the ones you need

NO1ennn

25,798 Aufrufe • vor 8 Tagen

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.
4:22

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.

SGLang

250,333 Aufrufe • vor 6 Tagen

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.
1:02

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 Aufrufe • vor 16 Tagen

Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For example, you can give it a set of possible choices, and Jev will classify the input text based on those choices, including a confidence score for each. Best of all: Jev is really fast and cheap, so you can use it in all sorts of applications. The first thing I built with it is a classifier to pick the hotels I want to visit. I use Apify to collect thousands of reviews, then classify them with Jev based on specific criteria I care about. You just couldn't do this reliably, but now you can. Link to the repository:
6:57

Jev is incredibly good! If you haven't heard, Jev is a new "System One" model optimized for decision-making. For example, you can give it a set of possible choices, and Jev will classify the input text based on those choices, including a confidence score for each. Best of all: Jev is really fast and cheap, so you can use it in all sorts of applications. The first thing I built with it is a classifier to pick the hotels I want to visit. I use Apify to collect thousands of reviews, then classify them with Jev based on specific criteria I care about. You just couldn't do this reliably, but now you can. Link to the repository:

Santiago

17,898 Aufrufe • vor 7 Tagen

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency TypeSafe AI is building something really interesting
2:13

Okay so Jev can actually do computer use really well Without any screenshots, or LLMs and no Pixels leave my mac I dont even read the Dom elements A local CoreML model segments every button and UI element on screen. On-device OCR reads the labels. That text is all Jev gets. It returns a probability across those elements and tells me the best one to click. Then it clicks, re-runs detection, and decides again. In a loop until the goal is done. ~90ms per decision. Faster than any LLM computer use I've tried. Blazing fast computer use, without any latency TypeSafe AI is building something really interesting

Milind S

244,864 Aufrufe • vor 18 Tagen

TypeSafe AI's Diogo Almeida with a16z's Ben Horowitz and Martin Casado on Jev, the model built to live inside software: Diogo's elevator pitch for Jev is a simple question - where is all the automation? AI is unbelievably smart, but outside of chatbots and coding agents, it hardly touches any real work. His diagnosis is the industry built models that generate text for humans to read, and software can't consume that output. Jev reads natural language and returns a choice from a set of options with a confidence level assigned to each, so developers can build programs that reason about intent and make probabilistic decisions rather than relying on human interpretation. TypeSafe's philosophy is "We build prod, not God." 0:50 "Where the f**k is all the automation?" 2:50 Jev vs. Claude Code and Codex 6:55 Jev is a classifier and classifiers are sick 7:40 Chat vs. code: is Jev a slider? 9:00 Diogo: From mathlete to Kaggle to OpenAI 12:20 "We build prod, not God" 15:55 Reliability over demos 16:55 2021 thoughts: RLHF is AGI? 20:45 Optimizing for the wrong use case 21:50 Is the real world too messy to automate? 25:00 Nobody expected the Jev launch 26:35 Three kinds of reliability 28:05 Good at syntax, bad at architecture 30:00 The inverse SaaSpocalypse 33:40 Why coding agents automate so little 36:05 Probabilistic programming returns 38:45 Jev as the UDP-to-TCP layer for AI 40:20 The 5 stages of grief for embedding AI 41:30 Utopia: AI that actually does what you mean YouTube: Diogo Almeida TypeSafe AI benahorowitz.eth martin_casado
42:24

TypeSafe AI's Diogo Almeida with a16z's Ben Horowitz and Martin Casado on Jev, the model built to live inside software: Diogo's elevator pitch for Jev is a simple question - where is all the automation? AI is unbelievably smart, but outside of chatbots and coding agents, it hardly touches any real work. His diagnosis is the industry built models that generate text for humans to read, and software can't consume that output. Jev reads natural language and returns a choice from a set of options with a confidence level assigned to each, so developers can build programs that reason about intent and make probabilistic decisions rather than relying on human interpretation. TypeSafe's philosophy is "We build prod, not God." 0:50 "Where the f**k is all the automation?" 2:50 Jev vs. Claude Code and Codex 6:55 Jev is a classifier and classifiers are sick 7:40 Chat vs. code: is Jev a slider? 9:00 Diogo: From mathlete to Kaggle to OpenAI 12:20 "We build prod, not God" 15:55 Reliability over demos 16:55 2021 thoughts: RLHF is AGI? 20:45 Optimizing for the wrong use case 21:50 Is the real world too messy to automate? 25:00 Nobody expected the Jev launch 26:35 Three kinds of reliability 28:05 Good at syntax, bad at architecture 30:00 The inverse SaaSpocalypse 33:40 Why coding agents automate so little 36:05 Probabilistic programming returns 38:45 Jev as the UDP-to-TCP layer for AI 40:20 The 5 stages of grief for embedding AI 41:30 Utopia: AI that actually does what you mean YouTube: Diogo Almeida TypeSafe AI benahorowitz.eth martin_casado

a16z

261,502 Aufrufe • vor 7 Tagen

Jev has been exploding across GitHub since launch, here's what people have already built with it if you have API access and don't know where to start, copy this: jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars jev-ultrafast - browser agent that picks every click itself, only calling a text model when it actually needs to type something. 16,758 stars jev-doom-agent - real Chocolate Doom compiled to WebAssembly, two engines running the same map, Jev picking the tactical macro every frame jev-t-rex-runner - the Chrome dinosaur game you've procrastinated with a hundred times, now played entirely by Jev picking jump, duck, or keep running typesafe-chess - Jev vs a real search engine, two games, colors swapped. the search won both, but overruled Jev's first instinct on roughly half the moves jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back none of these ten generate a single word of text. every one of them returns a number against an answer someone already defined full setup below, then run the three-question test from the article before you build an eleventh
0:24

Jev has been exploding across GitHub since launch, here's what people have already built with it if you have API access and don't know where to start, copy this: jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars jev-ultrafast - browser agent that picks every click itself, only calling a text model when it actually needs to type something. 16,758 stars jev-doom-agent - real Chocolate Doom compiled to WebAssembly, two engines running the same map, Jev picking the tactical macro every frame jev-t-rex-runner - the Chrome dinosaur game you've procrastinated with a hundred times, now played entirely by Jev picking jump, duck, or keep running typesafe-chess - Jev vs a real search engine, two games, colors swapped. the search won both, but overruled Jev's first instinct on roughly half the moves jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back none of these ten generate a single word of text. every one of them returns a number against an answer someone already defined full setup below, then run the three-question test from the article before you build an eleventh

Ryven

276,722 Aufrufe • vor 12 Tagen

Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!
0:31

Holy crap, who the hell did this?!! Someone open-sourced a Jev-powered second brain for AI agents and lets you plug it straight into your own agent. GitHub's already at 925 stars, repo's called Hermes-Jev-Skills. You just run one install command, and Jev takes over every tiny decision your agent burns premium tokens on. Which model answers, which skill to load, which memories matter, what survives when context gets cut. Give it your computer or browser and it'll pick the next click, but only from actions you already marked safe. It'll sort your inbox into lanes, strip hidden prompt injections out of search results, and triage every message in ~0.4 seconds. Claude Code and Codex support - they threw that in too. No dependencies, no patching Hermes core, and your API key never touches the agent Link's right here: The catch? Jev itself is a paid cloud API. The skills run on your machine; the decisions don't. But hey, a decision costs a fraction of a cent, everything fails open if Jev goes down, and your expensive model finally gets to do only the thinking. Who needs a damn frontier model picking which file to open!

Archive

16,841 Aufrufe • vor 5 Tagen

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓
0:24

Jev has been blowing up lately. If you've got the Jev API but don't know how to play around with it yet, you can just copy this checklist. 1. jev-ultrafast A high-speed browser Agent built with Browser Use. Jev only judges "what to do, which element to click" at each step, and only calls the small model when typing is needed. Searching for a flight on Google Flights takes about 7 seconds. 2. fast-jev-compaction Context compression for Claude Code. Before each tool call, have Jev judge if there's anything still useful; delete the useless stuff, and keep the original text without rewriting it. 3. json-render Vercel Labs' generative UI framework. In experiments, Jev doesn't write JSON token by token; it just handles selecting components, properties, and layouts. 4. typesafe-mcp Best for people who just got the API. Plug Jev into Claude Code, Claude Desktop, Codex, and Pi, and do Choice / Score / Noul anytime. 5. jev-mcp Ready-made Agent judgment toolkit: fact-checking, content screening, semantic ranking, classification, and information extraction. 6. SemDecide Turn Jev into a command-line tool. Directly classify, score, and filter in the Shell—great for hooking up to crawlers, CI, and data pipelines. 7. jev-codex-router First have Jev judge how hard this round of programming tasks is, then decide the model tier, reasoning depth, and speed mode. 8. Winnow Context garbage collection for Claude Code. When Read / Bash / Grep spits out a ton of stuff, Jev first judges which parts are really relevant to the current task. 9. jev-review Before code review, run it through Jev first to pick out high-risk changes, then hand them off to a pricier big model or a human. Comes with a local dashboard. 10. Blink Use Jev as a code repository navigator. At each directory level, judge which files are most relevant to the current issue, then keep digging down. Copy these complete Jev blueprints - then read full Jev setup below ↓ ↓

rody

202,492 Aufrufe • vor 14 Tagen

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.
0:31

The open-source local version of Laya crushes Jev in response speed! On the left is Laya, a local 421M open-source decision model. On the right is Jev 1.13.0, running through a cloud API. Same Snake game, same typed decisions, and the same 30-second free run: - Laya: Score 46, Length 52, 86.5 decisions/sec - Jev: Score 1, Length 7, 3.2 decisions/sec - In a real test on an M5 Pro, median latency was 15.3ms locally versus 298.1ms in the cloud, so nearly 20x faster. Laya uses around 1GB of memory, responds in milliseconds, and doesn’t depend on a network connection. While Jev waits for a cloud round-trip at every step, Laya makes each decision instantly on-device.

Simplifying AI

24,406 Aufrufe • vor 14 Tagen

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI TypeSafe AI CEO Diogo Almeida explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.
0:43

Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI TypeSafe AI CEO Diogo Almeida explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch.

Latent.Space

411,777 Aufrufe • vor 14 Tagen

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
0:22

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 Aufrufe • vor 7 Tagen