Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Introducing Drex - a lightning-fast decision model built to rival Jev. #1 on the Decision Index. (official scores tbd) winning 23 out of 40 benchmarks Architecture: Small Diffusion Model with RLAF Price: $0.04 per 1M input tokens (cheaper than Jev) Latency: less than a second. Sign up now for... show more

Nace AI

1,832 subscribers

639,893 görüntüleme • 1 ay önce •via X (Twitter)

Bilim & Teknoloji Finans

Anya Rossi• Live Now

Private livecam show

28 Yorum

Nace AI profil fotoğrafı

Nace AI1 ay önce

Try it now:

Nace AI profil fotoğrafı

Nace AI1 ay önce

Decision Index 0.2 results

Rahul profil fotoğrafı

Rahul1 ay önce

faster, cheaper, better than jev. definitely trying it

Nace AI profil fotoğrafı

Nace AI1 ay önce

would love to see what you build with it 👀

Rahul profil fotoğrafı

Rahul1 ay önce

yeah. signed up. thanks for $25 credit too :)

MAX profil fotoğrafı

MAX1 ay önce

$0.04 for 1M tokens is actually crazy cheap

Nace AI profil fotoğrafı

Nace AI1 ay önce

and we’re just getting started :)

Rohan Paul profil fotoğrafı

Rohan Paul1 ay önce

This is such a solid direction that we are seeing now. reserve expensive generative inference for the branches that actually require generation. everything else can potentially run through a cheaper decision layer.

painn profil fotoğrafı

painn1 ay önce

you guys are really cooking, i ll check it out with the 250M credits and give some feedback

Nace AI profil fotoğrafı

Nace AI1 ay önce

and we’re just getting started

painn profil fotoğrafı

painn1 ay önce

cook!!!!

Ahmad Bukhari | AI Systems Architect profil fotoğrafı

Ahmad Bukhari | AI Systems Architect1 ay önce

The promised open weights and report will make this easier to judge. Are you planning to publish the eval harness and training recipe too, or only the checkpoint? Those details determine what others can actually reproduce.

Noe Cruz profil fotoğrafı

Noe Cruz1 ay önce

Gaming is just the visible part. The thing worth watching is that it decides under time pressure with incomplete information — which is the actual bottleneck for anyone running something alone, not the producing.

Sakata profil fotoğrafı

Sakata1 ay önce

Rival jev? Count me innnn

ANURAG SINGH BHANDARI profil fotoğrafı

ANURAG SINGH BHANDARI1 ay önce

time to add drex

Vishesh Baghel profil fotoğrafı

Vishesh Baghel1 ay önce

looks super cool. I work on business workflows all day and drex looks a perfect fit for me. gonna cook something cool with this

Nace AI profil fotoğrafı

Nace AI1 ay önce

appreciate it 🤝 keep us posted on what you cook

JSON x profil fotoğrafı

JSON x1 ay önce

That was quick, also in stealth mode?

Nace AI profil fotoğrafı

Nace AI1 ay önce

👀

Straelight profil fotoğrafı

Straelight1 ay önce

ayt, lets go

David GC🏴‍☠️ profil fotoğrafı

David GC🏴‍☠️1 ay önce

I'm in!!!!

Chen profil fotoğrafı

Chen1 ay önce

23 out of 40 benchmarks won and it's already number 1? math checks out i guess.

Aryan SMM profil fotoğrafı

Aryan SMM1 ay önce

the small diffusion architecture is the part I’d be most curious to test

Morlex profil fotoğrafı

Morlex1 ay önce

it's look like warhammer 40 000

Asklv profil fotoğrafı

Asklv1 ay önce

How does Drex handle a changing action set? That’s the hard part we see in Jev Social—every browser step creates a new menu, so fixed-choice scores don’t always carry over.

𝙳𝚛𝚊𝚟𝚎𝚗 profil fotoğrafı

𝙳𝚛𝚊𝚟𝚎𝚗1 ay önce

Honestly it's too much crazy good cooked

Alan profil fotoğrafı

Alan1 ay önce

I am using it because this is better than jev

TheDirector profil fotoğrafı

TheDirector1 ay önce

I'd love to see it tried on our platform!

Benzer Videolar

Drex 1.5 is Live! 128k context window, more rivalry to Jev #1 on the Decision Index 0.2.1 + JevBench (SOTA) Absolute leader in long context decisions Latency: sub-second Decision models are getting better! Price: $0.04 per 1M input tokens Try Drex with 250M free tokens #drex #jev #nace

Drex 1.5 is Live! 128k context window, more rivalry to Jev #1 on the Decision Index 0.2.1 + JevBench (SOTA) Absolute leader in long context decisions Latency: sub-second Decision models are getting better! Price: $0.04 per 1M input tokens Try Drex with 250M free tokens #drex #jev #nace

Nace AI

541,219 görüntüleme • 1 ay önce

Introducing the Decision Index 0.1 ⚖️ a rigorous leaderboard comparing jev with 30+ open weights decision models 35+ benchmarks. asking 130K questions to each model testing knowledge 🧠, automation ⚙️, understanding 🤔and even creativity 🎨

Introducing the Decision Index 0.1 ⚖️ a rigorous leaderboard comparing jev with 30+ open weights decision models 35+ benchmarks. asking 130K questions to each model testing knowledge 🧠, automation ⚙️, understanding 🤔and even creativity 🎨

apolinario (poli)

44,399 görüntüleme • 1 ay önce

Introducing d3-turbo: our newest state-of-the-art multimodal foundation decision model⚡ #1 on both Jev Decision Index boards. It points(box), follows and sees images in your questions. StateOnce brings 15x faster than d3 flash 🤗 #vLLM #Jev #Decision

Introducing d3-turbo: our newest state-of-the-art multimodal foundation decision model⚡ #1 on both Jev Decision Index boards. It points(box), follows and sees images in your questions. StateOnce brings 15x faster than d3 flash 🤗 #vLLM #Jev #Decision

Xunzhuo

21,223 görüntüleme • 24 gün önce

Introducing SubQ Snap, the first long-context decision model for real enterprise work. Snap is the only decision model or LLM where compute per token stays constant as context grows. • 384K tokens of multimodal context, 12x larger than Jev. • 61.7 on Decision Index v0.2.1 vs Jev’s 57.9, outperforming on 13 of 16 enterprise benchmarks. •Processes 100K tokens and returns a decision in under one second. •$0.05/MM input tokens. Output is free. Available today to anyone. The first 10,000 sign-ups get 100M free input tokens. We’ll likely hit capacity fast and will add users as we add compute. Compute offers welcome 🙂. Latency will be variable as we tune the platform to this new model and category of users. Model speeds are 80ms for minimal context, 250ms for 32k, 660ms for 100k, and 2.5 seconds for 384k. Visit:

Introducing SubQ Snap, the first long-context decision model for real enterprise work. Snap is the only decision model or LLM where compute per token stays constant as context grows. • 384K tokens of multimodal context, 12x larger than Jev. • 61.7 on Decision Index v0.2.1 vs Jev’s 57.9, outperforming on 13 of 16 enterprise benchmarks. •Processes 100K tokens and returns a decision in under one second. •$0.05/MM input tokens. Output is free. Available today to anyone. The first 10,000 sign-ups get 100M free input tokens. We’ll likely hit capacity fast and will add users as we add compute. Compute offers welcome 🙂. Latency will be variable as we tune the platform to this new model and category of users. Model speeds are 80ms for minimal context, 250ms for 32k, 660ms for 100k, and 2.5 seconds for 384k. Visit:

Alexander Whedon

4,516,674 görüntüleme • 1 ay önce

Meet d3-ultra: our newest open 27B multimodal decision model. #2 of 230 on the Jev Decision Index text board, +3.03 over d3. Text, images, video: it boxes what it finds and tracks it through time. Open weights (Apache-2.0): #Jev #Decision

Meet d3-ultra: our newest open 27B multimodal decision model. #2 of 230 on the Jev Decision Index text board, +3.03 over d3. Text, images, video: it boxes what it finds and tracks it through time. Open weights (Apache-2.0): #Jev #Decision

Xunzhuo

12,534 görüntüleme • 16 gün önce

Introducing Decision 3.0: towards open multimodal foundation decision models ⚡ Open and state-of-the-art from 0.6B to 27B: #1 on both Jev Decision Index boards in our evaluation, on a new Pareto frontier. HF collection 🤗: #OpenSource #Jev #LLM

Introducing Decision 3.0: towards open multimodal foundation decision models ⚡ Open and state-of-the-art from 0.6B to 27B: #1 on both Jev Decision Index boards in our evaluation, on a new Pareto frontier. HF collection 🤗: #OpenSource #Jev #LLM

Xunzhuo

141,560 görüntüleme • 1 ay önce

Today, we are announcing Nimble-v4 and Nimble-v4-max which are pushing the frontier of decision models, outperforming Jev and other variants. On the Decision Index public scores, nimble-v4-max and nimble-v4 score +10 and +6 against Jev 1.13, making nimble-v4-max the #1 model. Beyond benchmarks, we have done a lot of internal evals, and see meaningful improvements: 43% fewer mistakes than Jev, 50pp improvement on model routing decisions, being great at coding use cases, fact checking etc. The models are available via our API service. Go build nimbly:

Today, we are announcing Nimble-v4 and Nimble-v4-max which are pushing the frontier of decision models, outperforming Jev and other variants. On the Decision Index public scores, nimble-v4-max and nimble-v4 score +10 and +6 against Jev 1.13, making nimble-v4-max the #1 model. Beyond benchmarks, we have done a lot of internal evals, and see meaningful improvements: 43% fewer mistakes than Jev, 50pp improvement on model routing decisions, being great at coding use cases, fact checking etc. The models are available via our API service. Go build nimbly:

Mahesh Sathiamoorthy

83,702 görüntüleme • 1 ay önce

first time in my life a company is giving me back more than i spent 💀 Drex Max is doing 120% cashback right now. spend $100 on Jev or any other decision model, get $120 back in Drex credits i thought it was a cheap model buying users with promos. it's not: → 78% on OSWorld-Verified, one point behind Opus 5.5 → a web task that costs $0.074 on Claude Code costs $0.015 on Drex → API is Jev compatible, so you only change 3 env vars almost same score, 5x cheaper, and you get paid to try it $25 free credits at + use code "ISRA10" for $10 more try here:

first time in my life a company is giving me back more than i spent 💀 Drex Max is doing 120% cashback right now. spend $100 on Jev or any other decision model, get $120 back in Drex credits i thought it was a cheap model buying users with promos. it's not: → 78% on OSWorld-Verified, one point behind Opus 5.5 → a web task that costs $0.074 on Claude Code costs $0.015 on Drex → API is Jev compatible, so you only change 3 env vars almost same score, 5x cheaper, and you get paid to try it $25 free credits at + use code "ISRA10" for $10 more try here:

Isra

11,592 görüntüleme • 8 gün önce

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

David Villalón

43,891 görüntüleme • 1 ay önce

Jev Engineering changes the unit of optimization from “agent” to “decision.” that sounds small, but it changes the architecture. and up to 193x faster and 444x cheaper in tests. normal multi-agent stack: agent → prompt → tool → output Jev-style stack: shared state → decision boundary → selected branch → execution → measurement → state update now you can optimize the actual control points: latency per decision cost per fork confidence threshold retry policy branch survival termination condition the agents underneath can change. the models can change. the tools can change. the decision layer stays measurable. that’s why Jev Engineering feels more like systems engineering than prompt engineering.

Jev Engineering changes the unit of optimization from “agent” to “decision.” that sounds small, but it changes the architecture. and up to 193x faster and 444x cheaper in tests. normal multi-agent stack: agent → prompt → tool → output Jev-style stack: shared state → decision boundary → selected branch → execution → measurement → state update now you can optimize the actual control points: latency per decision cost per fork confidence threshold retry policy branch survival termination condition the agents underneath can change. the models can change. the tools can change. the decision layer stays measurable. that’s why Jev Engineering feels more like systems engineering than prompt engineering.

Ricker

22,469 görüntüleme • 1 ay önce

Introducing Mercury Decide: the most intelligent decision model on OpenRouter (JevBench v1.4) and one of the fastest. Up to 14 decisions per second. Watch it go head-to-head with Jev in chess. Free for early access on OpenRouter:

Introducing Mercury Decide: the most intelligent decision model on OpenRouter (JevBench v1.4) and one of the fastest. Up to 14 decisions per second. Watch it go head-to-head with Jev in chess. Free for early access on OpenRouter:

Inception

20,338 görüntüleme • 1 ay önce

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

169,880 görüntüleme • 1 ay önce

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

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 görüntüleme • 1 ay önce

Jev model has been causing a sensation on GitHub ever since its release, and I am going to tell you about the best repositories that nobody is talking about How does this work: browser-use/browser-use⁠ - 32,500+ stars The core web automation library that houses the Jev integration ecosystem (including ⁠jev-ultrafast⁠). It enables AI decision models to directly control web browser actions, click DOM elements, and automate complex workflows without heavy LLM latency langchain-ai/langchain⁠ - 98,500+ stars Integrates Jev as an ultra-fast model router, guardrail evaluator, and safety firewall. Jev evaluates task risk, intent, and complexity before passing execution to heavy LLMs LiteLLM/litellm⁠ - 59,200+ stars A lightweight proxy and routing library for LLMs. It features native Jev decision-model routing to classify incoming prompts and instantly direct requests to the cheapest or fastest model endpoint dify-ai/dify⁠ - 58,000+ stars An open-source LLM application development platform that incorporates Jev-style decision nodes for instant conditional branching and typed classification in multi-agent workflows vllm-project/vllm⁠ - 36,000+ stars A high-throughput LLM serving engine widely used for self-hosting custom decision-model checkpoints (such as Qwen3.5-based Jev fine-tunes) with ultra-low latency logits evaluation QwenLM/Qwen⁠ - 18,500+ stars The open base model family (Qwen3.5/3.8) used to train open-source Jev-like decision models (like Kev and RSI-Jev) powering typed probabilistic choices directly from custom model weights 🔗 You will definitely find what you need. I recommend adding this to your bookmarks

Jev model has been causing a sensation on GitHub ever since its release, and I am going to tell you about the best repositories that nobody is talking about How does this work: browser-use/browser-use⁠ - 32,500+ stars The core web automation library that houses the Jev integration ecosystem (including ⁠jev-ultrafast⁠). It enables AI decision models to directly control web browser actions, click DOM elements, and automate complex workflows without heavy LLM latency langchain-ai/langchain⁠ - 98,500+ stars Integrates Jev as an ultra-fast model router, guardrail evaluator, and safety firewall. Jev evaluates task risk, intent, and complexity before passing execution to heavy LLMs LiteLLM/litellm⁠ - 59,200+ stars A lightweight proxy and routing library for LLMs. It features native Jev decision-model routing to classify incoming prompts and instantly direct requests to the cheapest or fastest model endpoint dify-ai/dify⁠ - 58,000+ stars An open-source LLM application development platform that incorporates Jev-style decision nodes for instant conditional branching and typed classification in multi-agent workflows vllm-project/vllm⁠ - 36,000+ stars A high-throughput LLM serving engine widely used for self-hosting custom decision-model checkpoints (such as Qwen3.5-based Jev fine-tunes) with ultra-low latency logits evaluation QwenLM/Qwen⁠ - 18,500+ stars The open base model family (Qwen3.5/3.8) used to train open-source Jev-like decision models (like Kev and RSI-Jev) powering typed probabilistic choices directly from custom model weights 🔗 You will definitely find what you need. I recommend adding this to your bookmarks

Bober_smart

20,161 görüntüleme • 1 ay önce

updated Decision Index 0.1 → 0.2 🎯 better formula, +29 jev-like models, +21 benchmarks AutoJev-27B by Perplexity CTO Denis Yarats took the open lead, trailing jev by 0.8 points 🏆 come find the best model at every size, speed and use-case

updated Decision Index 0.1 → 0.2 🎯 better formula, +29 jev-like models, +21 benchmarks AutoJev-27B by Perplexity CTO Denis Yarats took the open lead, trailing jev by 0.8 points 🏆 come find the best model at every size, speed and use-case

apolinario (poli)

24,255 görüntüleme • 1 ay önce

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

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

43,110 görüntüleme • 1 ay önce

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:

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 görüntüleme • 1 ay önce

Jev Engineering is what turns an agent stack into an actual control system and moves the expensive model out of every decision loop. and up to 193x faster and 444x cheaper in tests. the model shouldn’t decide everything. in this setup: request → structured state → Jev router → cheapest capable model → worker → relevance / approval checks → execution gate → tool the important part is that the decision layers don’t generate prose. they route → score → block → approve. so expensive models only get called when the task actually needs them. that’s the point of Jev Engineering: separate reasoning from decision-making, then make the decision layer measurable, cheap and fast. full breakdown in the article below ↓

Jev Engineering is what turns an agent stack into an actual control system and moves the expensive model out of every decision loop. and up to 193x faster and 444x cheaper in tests. the model shouldn’t decide everything. in this setup: request → structured state → Jev router → cheapest capable model → worker → relevance / approval checks → execution gate → tool the important part is that the decision layers don’t generate prose. they route → score → block → approve. so expensive models only get called when the task actually needs them. that’s the point of Jev Engineering: separate reasoning from decision-making, then make the decision layer measurable, cheap and fast. full breakdown in the article below ↓

Ricker

183,199 görüntüleme • 1 ay önce

the jev Decision Index v0.3 is here 🎯 featuring a way stronger set of benchmarks, now with a strong private half 🔒 so the ranking tracks skills beyond benchmarks and, as promised, vision 👁️

the jev Decision Index v0.3 is here 🎯 featuring a way stronger set of benchmarks, now with a strong private half 🔒 so the ranking tracks skills beyond benchmarks and, as promised, vision 👁️

apolinario (poli)

18,111 görüntüleme • 1 ay önce

Fun addition to transformers serve: you can now turn any of the 250 LLM & VLM model into a JEV-like decision model. /v1/systemone scores a set of decision with the model's logits. No need to generate text! Which one of them can get microducks across the finish line fast?

Fun addition to transformers serve: you can now turn any of the 250 LLM & VLM model into a JEV-like decision model. /v1/systemone scores a set of decision with the model's logits. No need to generate text! Which one of them can get microducks across the finish line fast?

Lysandre

16,114 görüntüleme • 1 ay önce