Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Why is everyone obsessed with an AI model that can't write? 🧠 TypeSafe launched Jev, a "System One" model that doesn't write text - it picks from answer options you define and returns a probability for each. ⚡ 20 questions cost about the same as one, because it reads...

zauey's profile picture

Claire Zau

124,900 subscribers

68,100 Aufrufe • vor 1 Monat •via TikTok

Wissenschaft & Technologie#ai#startups#tech#llm#devtools
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🧪 Try Jev free with KodeKey: Jev by TypeSafe is a System One AI model that answers your code with calibrated probabilities instead of text, and it doesn't charge for output tokens. Everyone's talking about the model. Almost nobody explains why it works the way it does. This video covers what a System One model actually is, why a normal LLM can't reliably tell you how sure it is, and how Jev keeps its answers tied to reality, plus where it saves you real money. Then it goes hands-on: a Papers, Please style game where Jev goes head to head with GPT-5.5 and DeepSeek to clear an approval queue on KodeKey. Stick around for the end, where you get everything you need to build the same demo yourself. 📚 What you'll learn: 1️⃣ Why a confidence score from a regular LLM can't be trusted, and what calibration really means 2️⃣ How Jev splits probability across choice, score and yes/no questions in a single pass 3️⃣ Confidence-gated routing: which tickets your code can act on alone and which need a human 4️⃣ Why Jev's output tokens are free, and how speculative fan-out answers five questions for the price of one 5️⃣ A game build where Jev, GPT-5.5 and DeepSeek approve and reject papers side by side
21:50

🧪 Try Jev free with KodeKey: Jev by TypeSafe is a System One AI model that answers your code with calibrated probabilities instead of text, and it doesn't charge for output tokens. Everyone's talking about the model. Almost nobody explains why it works the way it does. This video covers what a System One model actually is, why a normal LLM can't reliably tell you how sure it is, and how Jev keeps its answers tied to reality, plus where it saves you real money. Then it goes hands-on: a Papers, Please style game where Jev goes head to head with GPT-5.5 and DeepSeek to clear an approval queue on KodeKey. Stick around for the end, where you get everything you need to build the same demo yourself. 📚 What you'll learn: 1️⃣ Why a confidence score from a regular LLM can't be trusted, and what calibration really means 2️⃣ How Jev splits probability across choice, score and yes/no questions in a single pass 3️⃣ Confidence-gated routing: which tickets your code can act on alone and which need a human 4️⃣ Why Jev's output tokens are free, and how speculative fan-out answers five questions for the price of one 5️⃣ A game build where Jev, GPT-5.5 and DeepSeek approve and reject papers side by side

KodeKloud

14,600 Aufrufe • vor 1 Monat

A recap of notable startup activity from September 🚀 Comment “startup” for the full list and my analysis on Substack #ai #startups #venturecapital #tech #investing This list might not have every startup that raised in September. The numbers and charts are meant to show directional trends, not capture the entire market. Disclosure: Views expressed are my own. This is not investment advice. This is for informational and educational purposes only.
2:42

A recap of notable startup activity from September 🚀 Comment “startup” for the full list and my analysis on Substack #ai #startups #venturecapital #tech #investing This list might not have every startup that raised in September. The numbers and charts are meant to show directional trends, not capture the entire market. Disclosure: Views expressed are my own. This is not investment advice. This is for informational and educational purposes only.

Claire Zau

12,600 Aufrufe • vor 1 Monat

honestly this should be f*cking illegal your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago. Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs. 3 repos already built on it: -> jev-trader: one AI trade decision every single block, on a live MON-USDC market -> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading -> AIStock: "one person can become their own super-analyst" $0.042 per million input tokens. output is free. that's thousands of decisions for the price of one LLM call. the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first. > let the big model do the research. > let Jev pull the trigger. > let code set the stop. bookmark this before your bot is the slow one in the room.
0:25

honestly this should be f*cking illegal your LLM takes 30 seconds to think about a trade, but candle closed 29 seconds ago. Jev answers in 70 to 500 milliseconds. it can't write a word. it returns BUY / SELL / HOLD and a probability, and that's all a scalp needs. 3 repos already built on it: -> jev-trader: one AI trade decision every single block, on a live MON-USDC market -> QuantDinger: a full open-source AI trading OS with Jev built in. research, strategy, agent trading -> AIStock: "one person can become their own super-analyst" $0.042 per million input tokens. output is free. that's thousands of decisions for the price of one LLM call. the catch: fast is not the same as right. a wrong call in 200 milliseconds is still a wrong call. paper trade it first. > let the big model do the research. > let Jev pull the trigger. > let code set the stop. bookmark this before your bot is the slow one in the room.

kiosa

100,321 Aufrufe • vor 1 Monat

Fusion Models by robinhood:0xa92768863a55d8a0591709f7f5e594a249d36ea3, explained properly. Why a panel beats one model: Ask three models the same hard question and they disagree. The disagreement is the information, where they contradict each other is where one of them is wrong, and a judge can see it. OpenRouter shipped exactly this in June and their panels beat any single frontier model. Credit to them and their $10B sale to stripe. Why the same panel for everyone is the wrong shape: You don't have one best model. You have a best model per job. The one you trust for code is not the one you trust for writing, and neither is the one you'd pick for a five-line reply. A panel chosen per request, identical for every user, can't know that. A panel arranged around you can. The number that matters isn't price: It's cost per answer that works. Model A costs $4 per million tokens and gets your job right one time in four. Model B costs $10 and gets it right three times in four. Per answer you actually keep, A costs $16 and B costs $13. The cheap model was the expensive one. Everyone comparing price lists is measuring the wrong thing. You never rate anything: Stopping an answer halfway is a rating. Regenerating is a rating. Switching model and asking again is the loudest rating there is. Every one of those already writes a row we can learn from. The router learns which models earn your credits, per job, and tries a cheaper one now and then to check. Fusion only when it pays: Cost mode tries the cheap model first and escalates only if a judge says it failed. Performance mode fans out to your panel and merges. Most simple prompts never fuse. That's why it costs less, not more. Put it together and you have a personal model: Not trained. Assembled. Your profile from a two-minute questionnaire and everything you've imported from Claude or ChatGPT. Your memory, shared across every model so switching never starts from zero. Your skills, workflows you build once and run on any model. Your scorecard, which models earn your credits per job. One per person. Nobody else has yours. Every model is someone else's; the arrangement is you, and it leaves with you. People aren't loyal to models. They're loyal to results. A moat can't be a commodity, but it can be our own creation.
0:46

Fusion Models by robinhood:0xa92768863a55d8a0591709f7f5e594a249d36ea3, explained properly. Why a panel beats one model: Ask three models the same hard question and they disagree. The disagreement is the information, where they contradict each other is where one of them is wrong, and a judge can see it. OpenRouter shipped exactly this in June and their panels beat any single frontier model. Credit to them and their $10B sale to stripe. Why the same panel for everyone is the wrong shape: You don't have one best model. You have a best model per job. The one you trust for code is not the one you trust for writing, and neither is the one you'd pick for a five-line reply. A panel chosen per request, identical for every user, can't know that. A panel arranged around you can. The number that matters isn't price: It's cost per answer that works. Model A costs $4 per million tokens and gets your job right one time in four. Model B costs $10 and gets it right three times in four. Per answer you actually keep, A costs $16 and B costs $13. The cheap model was the expensive one. Everyone comparing price lists is measuring the wrong thing. You never rate anything: Stopping an answer halfway is a rating. Regenerating is a rating. Switching model and asking again is the loudest rating there is. Every one of those already writes a row we can learn from. The router learns which models earn your credits, per job, and tries a cheaper one now and then to check. Fusion only when it pays: Cost mode tries the cheap model first and escalates only if a judge says it failed. Performance mode fans out to your panel and merges. Most simple prompts never fuse. That's why it costs less, not more. Put it together and you have a personal model: Not trained. Assembled. Your profile from a two-minute questionnaire and everything you've imported from Claude or ChatGPT. Your memory, shared across every model so switching never starts from zero. Your skills, workflows you build once and run on any model. Your scorecard, which models earn your credits per job. One per person. Nobody else has yours. Every model is someone else's; the arrangement is you, and it leaves with you. People aren't loyal to models. They're loyal to results. A moat can't be a commodity, but it can be our own creation.

askr

13,924 Aufrufe • vor 1 Monat

We just launched Telnyx Decision Models in beta. AI agents make small judgment calls on every run. Is this caller asking for a refund? Which team owns this ticket? Is this incident urgent enough to page someone? Decision Models answers them in one API call. Send the context and up to 64 typed questions, and get typed answers back: a choice, a yes/no score, or a rating on a scale. Your code branches on the answer. There's no free text to parse. We are offering 2 models, chosen per request: → Decision Flash, the default, for high-volume routing and triage at the lowest cost and latency. $0.035 per 1M input tokens. → Decision Pro, for decisions that depend on long context, like a full support history or a long call transcript. $0.20 per 1M input tokens. Output tokens are free on both. The API is TypeSafe-compatible, so teams already using the TypeSafe SDK can point it at Telnyx with a new base URL and model name. It runs on the same API key as Telnyx voice, speech-to-text, and inference, so you don’t need to join any waitlist or go through extra setup to access it. Try it today:
0:39

We just launched Telnyx Decision Models in beta. AI agents make small judgment calls on every run. Is this caller asking for a refund? Which team owns this ticket? Is this incident urgent enough to page someone? Decision Models answers them in one API call. Send the context and up to 64 typed questions, and get typed answers back: a choice, a yes/no score, or a rating on a scale. Your code branches on the answer. There's no free text to parse. We are offering 2 models, chosen per request: → Decision Flash, the default, for high-volume routing and triage at the lowest cost and latency. $0.035 per 1M input tokens. → Decision Pro, for decisions that depend on long context, like a full support history or a long call transcript. $0.20 per 1M input tokens. Output tokens are free on both. The API is TypeSafe-compatible, so teams already using the TypeSafe SDK can point it at Telnyx with a new base URL and model name. It runs on the same API key as Telnyx voice, speech-to-text, and inference, so you don’t need to join any waitlist or go through extra setup to access it. Try it today:

Telnyx

866,229 Aufrufe • vor 1 Monat

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:
5:20

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 Aufrufe • vor 1 Monat

Microsoft launched an AI model on October 9th that it claims runs 35 times faster than OpenAI's GPT-6 and charges 4.2 cents per million input tokens with output completely free. The engine under the hood is Alibaba's open-weight Qwen 3.5 at 9 billion parameters, post-trained by Microsoft. Xbox used it to sort 10,000 pieces of player feedback at 14x the speed and 200x lower cost than GPT-6. The trick is that it never generates text at all. A standard LLM writes one token at a time - a 200-token answer means 200 forward passes through the entire network. Decision One reads the raw logit scores from the model's last layer for each option label, runs one softmax pass, and returns a probability distribution in a single forward pass. No generation, no chain-of-thought, just a confidence score. Agents that chain 50 decisions through a standard model take 75 seconds. At 35x speed that drops to 2 seconds. The formula for when to act versus escalate to a human: act when confidence P beats 1 minus human review cost divided by error cost. 5 minutes. Bookmark & watch today. The architecture decision that makes AI agents 35x faster and the one formula every agent builder needs.
5:13

Microsoft launched an AI model on October 9th that it claims runs 35 times faster than OpenAI's GPT-6 and charges 4.2 cents per million input tokens with output completely free. The engine under the hood is Alibaba's open-weight Qwen 3.5 at 9 billion parameters, post-trained by Microsoft. Xbox used it to sort 10,000 pieces of player feedback at 14x the speed and 200x lower cost than GPT-6. The trick is that it never generates text at all. A standard LLM writes one token at a time - a 200-token answer means 200 forward passes through the entire network. Decision One reads the raw logit scores from the model's last layer for each option label, runs one softmax pass, and returns a probability distribution in a single forward pass. No generation, no chain-of-thought, just a confidence score. Agents that chain 50 decisions through a standard model take 75 seconds. At 35x speed that drops to 2 seconds. The formula for when to act versus escalate to a human: act when confidence P beats 1 minus human review cost divided by error cost. 5 minutes. Bookmark & watch today. The architecture decision that makes AI agents 35x faster and the one formula every agent builder needs.

Eron

15,522 Aufrufe • vor 1 Monat

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

42,183 Aufrufe • vor 1 Monat

What Jev actually is, why it's so fast, and what you can build with it. Classification is as old as AI that can read: give it text, ask a question with fixed answers (complaint yes/no · which team · urgency 1–5), and the label drives a rule. The problem: we've been using models built for writing, a few seconds per answer. Jev (TypeSafe, launched Sept 15, founded by one of the OpenAI researchers behind ChatGPT's instruction-following) only decides. It never writes. Send the text once with every question; it scores every answer in one pass: yes/no, pick one, or a score, each with a confidence. 70–500 ms. Input ~$0.042 per million tokens, output free. TypeSafe measured up to ~200× faster and ~400× cheaper than top models on its own workflows, and says real-world gains are usually lower. Builders: a resume screened against 6,000+ companies in 25 seconds for $0.37; 98,000 items labeled in ten minutes. ~13% of paid Vercel AI Gateway teams used it within a day. Calibrated: "70% sure" should be right ~70% of the time, so software can act alone above a threshold and route the rest to a person. Build with it: every competitor ad, same five questions · every ticket, review, call note and CRM entry across systems, tagged the same way · an agent's actions checked before they run (LangChain already does this). Edges: text only; weak at math, counting, dates; reads your question literally; you design the questions and categories up front. That design is the skill. #jev #aiagent
2:56

What Jev actually is, why it's so fast, and what you can build with it. Classification is as old as AI that can read: give it text, ask a question with fixed answers (complaint yes/no · which team · urgency 1–5), and the label drives a rule. The problem: we've been using models built for writing, a few seconds per answer. Jev (TypeSafe, launched Sept 15, founded by one of the OpenAI researchers behind ChatGPT's instruction-following) only decides. It never writes. Send the text once with every question; it scores every answer in one pass: yes/no, pick one, or a score, each with a confidence. 70–500 ms. Input ~$0.042 per million tokens, output free. TypeSafe measured up to ~200× faster and ~400× cheaper than top models on its own workflows, and says real-world gains are usually lower. Builders: a resume screened against 6,000+ companies in 25 seconds for $0.37; 98,000 items labeled in ten minutes. ~13% of paid Vercel AI Gateway teams used it within a day. Calibrated: "70% sure" should be right ~70% of the time, so software can act alone above a threshold and route the rest to a person. Build with it: every competitor ad, same five questions · every ticket, review, call note and CRM entry across systems, tagged the same way · an agent's actions checked before they run (LangChain already does this). Edges: text only; weak at math, counting, dates; reads your question literally; you design the questions and categories up front. That design is the skill. #jev #aiagent

Professor Glitch

38,700 Aufrufe • vor 1 Monat

Jev (join the waitlist on the homepage): Half your AI bill is one-word answers. Yes or no. Spam or not. Which bucket. You're paying a frontier model for that. Jev is built for exactly those jobs. You give it the options. It picks one in under half a second. It never writes a sentence. So it can't make stuff up. The answer has to be on your list. 444 times cheaper. 193 times faster. Like a light switch instead of a dimmer. It only has to do one thing. Hand it the boring jobs. Save the big models for real thinking. #jev #aimodel #llm #artificialintelligence #aitools
0:40

Jev (join the waitlist on the homepage): Half your AI bill is one-word answers. Yes or no. Spam or not. Which bucket. You're paying a frontier model for that. Jev is built for exactly those jobs. You give it the options. It picks one in under half a second. It never writes a sentence. So it can't make stuff up. The answer has to be on your list. 444 times cheaper. 193 times faster. Like a light switch instead of a dimmer. It only has to do one thing. Hand it the boring jobs. Save the big models for real thinking. #jev #aimodel #llm #artificialintelligence #aitools

jackroberts____

20,000 Aufrufe • vor 1 Monat

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

416,758 Aufrufe • vor 1 Monat

Perplexity CEO Aravind Srinivas on the brutal truth about who actually makes money in AI (and why it's not who you think): Aravind argues that the real value in AI comes from orchestration. He points to products like Codex, Claude Code, and Perplexity Computer: "What is that? It's an orchestration system. It takes a model, pairs it with an agent harness." And what is an agent harness? "The simplest way of describing it is like rules for how the agent loop should run. What are all the skills and sub-agents and connectors and tools it accesses? Without the harness, you don't necessarily capture and convert the intrinsic intelligence in the model into valuable output tokens." This leads to a blunt conclusion about who has a real business in AI, and who doesn't: "If you're literally just a reseller of model tokens, you have no business, because the model will get commoditized. So even if you're a model builder, you don't have a business. As an infra layer, you have some business on serving those output tokens. But as an application layer or model builder, you don't really have a business if you're just a reseller of tokens that come directly out of the model." So where does the value accrue? "You have a business if you know how to take the model, ground it in valuable context, orchestrate it with a really good agent harness, connected to the right set of tools and connectors (whether it's personal connectors or business connectors) and provide the experience to people in one single unified system." Aravind Srinivas then explains Perplexity's specific edge: Beyond orchestrating across tools, files, and connectors, they also orchestrate across models. "That is the differentiation that Anthropic and OpenAI cannot claim, because you wouldn't find GPT-5 inside the Claude Code harness. You wouldn't find Claude Opus inside the Codex harness. These are competing with each other. Whereas you would find both these models inside Perplexity Computer." Why does this matter? Because it all comes down to power. In Aravind's framing, the fundamental cost driver in AI is watts (the one input nobody can subsidize except the government). "Whoever provides the most valuable output tokens with the least amount of power expended to produce them generates the greatest value to the end user, has the most pricing power, has the most value. That is the orchestration problem to solve." His conclusion: "The one single most important metric in AI is token value per watt per user."
2:50

Perplexity CEO Aravind Srinivas on the brutal truth about who actually makes money in AI (and why it's not who you think): Aravind argues that the real value in AI comes from orchestration. He points to products like Codex, Claude Code, and Perplexity Computer: "What is that? It's an orchestration system. It takes a model, pairs it with an agent harness." And what is an agent harness? "The simplest way of describing it is like rules for how the agent loop should run. What are all the skills and sub-agents and connectors and tools it accesses? Without the harness, you don't necessarily capture and convert the intrinsic intelligence in the model into valuable output tokens." This leads to a blunt conclusion about who has a real business in AI, and who doesn't: "If you're literally just a reseller of model tokens, you have no business, because the model will get commoditized. So even if you're a model builder, you don't have a business. As an infra layer, you have some business on serving those output tokens. But as an application layer or model builder, you don't really have a business if you're just a reseller of tokens that come directly out of the model." So where does the value accrue? "You have a business if you know how to take the model, ground it in valuable context, orchestrate it with a really good agent harness, connected to the right set of tools and connectors (whether it's personal connectors or business connectors) and provide the experience to people in one single unified system." Aravind Srinivas then explains Perplexity's specific edge: Beyond orchestrating across tools, files, and connectors, they also orchestrate across models. "That is the differentiation that Anthropic and OpenAI cannot claim, because you wouldn't find GPT-5 inside the Claude Code harness. You wouldn't find Claude Opus inside the Codex harness. These are competing with each other. Whereas you would find both these models inside Perplexity Computer." Why does this matter? Because it all comes down to power. In Aravind's framing, the fundamental cost driver in AI is watts (the one input nobody can subsidize except the government). "Whoever provides the most valuable output tokens with the least amount of power expended to produce them generates the greatest value to the end user, has the most pricing power, has the most value. That is the orchestration problem to solve." His conclusion: "The one single most important metric in AI is token value per watt per user."

Big Brain AI

42,634 Aufrufe • vor 3 Monaten

Tencent's Hy3 lands today with real coding and agent ability and a price that undercuts the models you'd put it against. It's a 295B MoE with only 21B active parameters, a big part of why it stays cheap to serve, plus a 256K context window and an Apache 2.0 license that even outperforms GLM-5.1 although GLM is 2.5x larger. On OpenRouter it runs at $0.14 per million input tokens and $0.58 per million output. For a model Tencent benchmarks against much larger flagships, that pricing is insane. Price-performance-ratio is China's real moat. I already wrote about Tencent Hy3 earlier and the significant leap in quality it represents. Therefore, I'm pleased to recommend this model from Tencent Hy. Open Router link down below: #Hy3 #Hunyuan #AICoding
0:45

Tencent's Hy3 lands today with real coding and agent ability and a price that undercuts the models you'd put it against. It's a 295B MoE with only 21B active parameters, a big part of why it stays cheap to serve, plus a 256K context window and an Apache 2.0 license that even outperforms GLM-5.1 although GLM is 2.5x larger. On OpenRouter it runs at $0.14 per million input tokens and $0.58 per million output. For a model Tencent benchmarks against much larger flagships, that pricing is insane. Price-performance-ratio is China's real moat. I already wrote about Tencent Hy3 earlier and the significant leap in quality it represents. Therefore, I'm pleased to recommend this model from Tencent Hy. Open Router link down below: #Hy3 #Hunyuan #AICoding

Chubby♨️

23,439 Aufrufe • vor 4 Monaten

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

43,110 Aufrufe • vor 1 Monat

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 coax out of a chat model.
0:24

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 coax out of a chat model.

Venice

553,215 Aufrufe • vor 1 Monat

⚡️ JUST IN: MUSK LAUNCHES GROK 4.5, CALLING IT "OPUS-CLASS" AI MODEL Musk just released Grok 4.5 on Grok Build, Cursor, and the SpaceXAI Console, calling it an "Opus-class" AI model. He says it is faster, more token-efficient and lower cost, with EU access expected by mid-July. Built on a 1.5 TRILLION parameter foundation model, it drops the same day as OpenAI's GPT-5.6. API pricing is $2 per million input tokens and $6 per million output tokens.
0:55

⚡️ JUST IN: MUSK LAUNCHES GROK 4.5, CALLING IT "OPUS-CLASS" AI MODEL Musk just released Grok 4.5 on Grok Build, Cursor, and the SpaceXAI Console, calling it an "Opus-class" AI model. He says it is faster, more token-efficient and lower cost, with EU access expected by mid-July. Built on a 1.5 TRILLION parameter foundation model, it drops the same day as OpenAI's GPT-5.6. API pricing is $2 per million input tokens and $6 per million output tokens.

Coin Bureau

50,488 Aufrufe • vor 4 Monaten

Who is Nvidia's “biggest challenger” (that is still a long way behind)? 📉 In 2014 AMD was losing money and its stock traded for a few dollars, then Lisa Su bet the company on a new chip design 🏆 A decade later it takes nearly half of all server CPU revenue, up from almost none 🧩 Now it's tackling the AI chip space with a chip built modularly that they say holds 50% more memory than Nvidia's newest 🔓 Its software ROCm is open and free, but most AI runs on CUDA, which only works on Nvidia chips #AMD #Nvidia #AI #Tech #Chips Disclosure: Views expressed are my own. This is for informational and educational purposes only.
2:15

Who is Nvidia's “biggest challenger” (that is still a long way behind)? 📉 In 2014 AMD was losing money and its stock traded for a few dollars, then Lisa Su bet the company on a new chip design 🏆 A decade later it takes nearly half of all server CPU revenue, up from almost none 🧩 Now it's tackling the AI chip space with a chip built modularly that they say holds 50% more memory than Nvidia's newest 🔓 Its software ROCm is open and free, but most AI runs on CUDA, which only works on Nvidia chips #AMD #Nvidia #AI #Tech #Chips Disclosure: Views expressed are my own. This is for informational and educational purposes only.

Claire Zau

59,800 Aufrufe • vor 1 Tag

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

247,546 Aufrufe • vor 1 Monat

TypeSafe AI released Jev. I truly believe this is a game changing kind of AI model. No joke. It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper! It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs. Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs. Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.
9:33

TypeSafe AI released Jev. I truly believe this is a game changing kind of AI model. No joke. It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper! It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs. Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs. Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.

Maximilian

43,939 Aufrufe • vor 1 Monat

Introducing *Switch*: a *harness framework* for *decision models* like Jev I looked for this the other day and was surprised to not find anything like it You obviously cannot use a decision model like an LLM in a coding agent harness like Pi, because Jev cannot generate tool calls But what if there was a framework that "generated the tool calls" for it programmatically, and Jev only had to pick out of that finite set of choices That is what switch does. You pick a "domain" to implement the decision model in, and it provides a core API to define your state, and the functions that will derive decision model questions out of that state. Chess is a domain, as well as being a rubric judge for evals It basically standardizes what I imagine a lot of people are already vibe-coding, to an abstract interface: calling a decision-model API through multiple steps, i.e. an agent loop over finite choices Because of the finiteness of the output of a decision model, you cannot have a general pure decision model harness. Instead, you need to implement specific ones that generate the choices programmatically (or have an LLM generate the choices, but I find the former more interesting) A primary use case I have for this is use as a judge in an eval. For example, At the end of a task run that involves a bunch of documents, most people currently follow this approach: extract text out of PDF/docx/md files, and dump them right into the context But what if the visual formatting of the output is a judging criterion? Then you have to dump an image of every page in the input state. But what if you have 200 pages, and your question does not need looking at all of them? What if Jev could navigate through the haystack and find the info it needs? I have noticed that Jev is not so good at chess nor being a Decision-Model-as-a-Judge. It sucks at chess, and it does not perform well enough to replace GPT 6.1 Sol as a judge in the domain I am working for But switch is not only for Jev! It is for any decision model including the ones supported by the pi-ai package So once you can generate enough data with a better model, you should be able to pick an open source one and fine-tune it on your use case to perform better! And the model should be trained in a harness like switch's to be especially performant and cost-efficient I wanted to get this out because I find the idea very exciting, at least for benchmarking. Jev is currently not there, but decision models obviously will be there at some point, and we can take them there! There are also a lot of potential gains from picking a specific domain, and creating a looping agent that does a job for 100x cheaper! Let me know if you have any ideas, I am quite keen to try this on new domains! Repo:
2:31

Introducing *Switch*: a *harness framework* for *decision models* like Jev I looked for this the other day and was surprised to not find anything like it You obviously cannot use a decision model like an LLM in a coding agent harness like Pi, because Jev cannot generate tool calls But what if there was a framework that "generated the tool calls" for it programmatically, and Jev only had to pick out of that finite set of choices That is what switch does. You pick a "domain" to implement the decision model in, and it provides a core API to define your state, and the functions that will derive decision model questions out of that state. Chess is a domain, as well as being a rubric judge for evals It basically standardizes what I imagine a lot of people are already vibe-coding, to an abstract interface: calling a decision-model API through multiple steps, i.e. an agent loop over finite choices Because of the finiteness of the output of a decision model, you cannot have a general pure decision model harness. Instead, you need to implement specific ones that generate the choices programmatically (or have an LLM generate the choices, but I find the former more interesting) A primary use case I have for this is use as a judge in an eval. For example, At the end of a task run that involves a bunch of documents, most people currently follow this approach: extract text out of PDF/docx/md files, and dump them right into the context But what if the visual formatting of the output is a judging criterion? Then you have to dump an image of every page in the input state. But what if you have 200 pages, and your question does not need looking at all of them? What if Jev could navigate through the haystack and find the info it needs? I have noticed that Jev is not so good at chess nor being a Decision-Model-as-a-Judge. It sucks at chess, and it does not perform well enough to replace GPT 6.1 Sol as a judge in the domain I am working for But switch is not only for Jev! It is for any decision model including the ones supported by the pi-ai package So once you can generate enough data with a better model, you should be able to pick an open source one and fine-tune it on your use case to perform better! And the model should be trained in a harness like switch's to be especially performant and cost-efficient I wanted to get this out because I find the idea very exciting, at least for benchmarking. Jev is currently not there, but decision models obviously will be there at some point, and we can take them there! There are also a lot of potential gains from picking a specific domain, and creating a looping agent that does a job for 100x cheaper! Let me know if you have any ideas, I am quite keen to try this on new domains! Repo:

Onur Solmaz

106,096 Aufrufe • vor 16 Tagen