Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Jev with Exa is INSANE. > Jev without websearch confidently gives wrong outputs > Jev with websearch is literally much more accurate Try Jev (with Exa websearch) for free 👇

Ishan Goswami

15,357 subscribers

203,742 Aufrufe • vor 1 Monat •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Why is nobody posting about this? This is hands down the BEST way to run Jev right now. You can use the new Jev Playground to start running decisions with Jev for FREE. You're welcome. →

Why is nobody posting about this? This is hands down the BEST way to run Jev right now. You can use the new Jev Playground to start running decisions with Jev for FREE. You're welcome. →

Miles Deutscher

37,131 Aufrufe • vor 1 Monat

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Duncan

120,065 Aufrufe • vor 1 Monat

Jev is INSANE 😳 you can use Jev for FREE on OpenRouter it scanned 471 news stories in 31.9 seconds and picked 15 brands worth jumping on - 471 headlines scanned - 15 brand opportunities found - 31.9 seconds - $0.0065 total cost > Claude Opus 5: 17/471 > cost: $0.386 > roughly 1,650x cheaper per headline try Jev here:

K2S

15,167 Aufrufe • vor 1 Monat

Introducing Amos 1, four open-weight decision models from 0.5B to 27B. > 94.9% on Decision Bench, ahead of Perplexity, Gemini and Jev > beats Jev by 10 points on JevBench hard > reads photos and answers with boxes > decisions in 27 to 122 ms, free API, Apache 2.0

Introducing Amos 1, four open-weight decision models from 0.5B to 27B. > 94.9% on Decision Bench, ahead of Perplexity, Gemini and Jev > beats Jev by 10 points on JevBench hard > reads photos and answers with boxes > decisions in 27 to 122 ms, free API, Apache 2.0

Zaid

36,280 Aufrufe • vor 1 Monat

After playing with the Jev hybrid model, I started looking into OpenJev, and started with a halite 1 implementation with: GLM 5.3 Flash + Jev [vs] GLM 5.3 Flash + OpenJev OpenJev is just a 4B model handily defeating Jev (in this tiny silly toy example ofc). Now I'm super curious to learn what Jev's actual model size is.

After playing with the Jev hybrid model, I started looking into OpenJev, and started with a halite 1 implementation with: GLM 5.3 Flash + Jev [vs] GLM 5.3 Flash + OpenJev OpenJev is just a 4B model handily defeating Jev (in this tiny silly toy example ofc). Now I'm super curious to learn what Jev's actual model size is.

Harrison Kinsley

25,596 Aufrufe • vor 1 Monat

The gains aren’t free: Jev can't generate text Comparing Jev vs LLMs side-by-side makes the trade-off clear Fun fact: replacing sequential computation with parallel is the same way Transformers leapfrogged RNNs

The gains aren’t free: Jev can't generate text Comparing Jev vs LLMs side-by-side makes the trade-off clear Fun fact: replacing sequential computation with parallel is the same way Transformers leapfrogged RNNs

Diogo Almeida

2,118,707 Aufrufe • vor 2 Monaten

This is absolutely f*cking insane. you can put a $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.

This is absolutely f*cking insane. you can put a $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.

kiosa

11,388 Aufrufe • vor 22 Tagen

I built JevSearch, search the web & validate your results with Jev. Give a query and selection criteria, use Browserbase search to get the t25 results, then Jev scores and returns the t5 results. Jev often chooses urls outside of the initial top 5 as more relevant.

I built JevSearch, search the web & validate your results with Jev. Give a query and selection criteria, use Browserbase search to get the t25 results, then Jev scores and returns the t5 results. Jev often chooses urls outside of the initial top 5 as more relevant.

Kyle Jeong

60,133 Aufrufe • vor 1 Monat

Jev dropped and people immediately started doing stupid sh*t with it people gave this thing trading bots, browsers, Doom, drones, dinosaurs and tax forms and basically said: “you decide.” here’s what happened: > jev-trader Jev gets a new Monad block every ~300ms and decides whether to place a live limit order. no essay. just the decision. 1,911 stars ▸ ⁠ > jev-ultrafast a browser agent where Jev decides every click. the text model only wakes up when something actually needs to be written. 16,758 stars ▸ ⁠ > jev-doom-agent someone compiled actual Chocolate Doom to WebAssembly and let Jev make the tactical decisions every frame. yes. Doom. ▸ ⁠ > jev-t-rex-runner remember that stupid Chrome dinosaur? now Jev plays it. jump → duck → run → repeat ▸ ⁠ > typesafe-chess Jev went against a real chess search engine. two games. colors swapped. the search engine won both — and overruled Jev’s first instinct on roughly half the moves. ▸ ⁠ > jev-drone camera → Jev → drone. a simulated quadrotor has to clear five stations while Jev looks at the situation twice a second and decides what happens next. ▸ ⁠ > tax-doc-classifier then someone gave it IRS forms. 261 documents. 100% strict accuracy. roughly $0.001/page. ▸ ⁠ > killmyidea this one is evil lol tell it your startup idea. Jev looks at it from different angles and gives you: KILL / FIX / SHIP ▸ ⁠ > jev-curate throw huge Parquet / JSONL datasets at it. Jev judges 1,500+ rows/sec and keeps only the stuff that passes your rules. ▸ ⁠ > pg-jev and now it’s inside PostgreSQL. ask questions about your own tables in plain English → get the decision back. ▸ ⁠ and this is the weird part: none of these need Jev to write you a beautiful paragraph. they need it to look at a situation and pick: BUY / WAIT CLICK A / CLICK B JUMP / DUCK KILL / FIX / SHIP KEEP / DROP that’s basically the whole Jev idea. LLMs think and write. Jev decides. code does. full setup + my three-question Jev test below

Jev dropped and people immediately started doing stupid sh*t with it people gave this thing trading bots, browsers, Doom, drones, dinosaurs and tax forms and basically said: “you decide.” here’s what happened: > jev-trader Jev gets a new Monad block every ~300ms and decides whether to place a live limit order. no essay. just the decision. 1,911 stars ▸ ⁠ > jev-ultrafast a browser agent where Jev decides every click. the text model only wakes up when something actually needs to be written. 16,758 stars ▸ ⁠ > jev-doom-agent someone compiled actual Chocolate Doom to WebAssembly and let Jev make the tactical decisions every frame. yes. Doom. ▸ ⁠ > jev-t-rex-runner remember that stupid Chrome dinosaur? now Jev plays it. jump → duck → run → repeat ▸ ⁠ > typesafe-chess Jev went against a real chess search engine. two games. colors swapped. the search engine won both — and overruled Jev’s first instinct on roughly half the moves. ▸ ⁠ > jev-drone camera → Jev → drone. a simulated quadrotor has to clear five stations while Jev looks at the situation twice a second and decides what happens next. ▸ ⁠ > tax-doc-classifier then someone gave it IRS forms. 261 documents. 100% strict accuracy. roughly $0.001/page. ▸ ⁠ > killmyidea this one is evil lol tell it your startup idea. Jev looks at it from different angles and gives you: KILL / FIX / SHIP ▸ ⁠ > jev-curate throw huge Parquet / JSONL datasets at it. Jev judges 1,500+ rows/sec and keeps only the stuff that passes your rules. ▸ ⁠ > pg-jev and now it’s inside PostgreSQL. ask questions about your own tables in plain English → get the decision back. ▸ ⁠ and this is the weird part: none of these need Jev to write you a beautiful paragraph. they need it to look at a situation and pick: BUY / WAIT CLICK A / CLICK B JUMP / DUCK KILL / FIX / SHIP KEEP / DROP that’s basically the whole Jev idea. LLMs think and write. Jev decides. code does. full setup + my three-question Jev test below

kiosa

67,916 Aufrufe • vor 1 Monat

Made a real-time slop detector with jev as you scroll

Made a real-time slop detector with jev as you scroll

Robin Bilgil

791,552 Aufrufe • vor 1 Monat

What can you build with Jev? Practical use cases for fast, cheap decision models.

What can you build with Jev? Practical use cases for fast, cheap decision models.

Rubric Labs

16,295 Aufrufe • vor 1 Monat

We found the perfect use case for Jev: auto-routing GenAI models. The idea: Jev picks the most cost-effective models for your task, balancing speed and quality. All generations made with Higgsfield API.

We found the perfect use case for Jev: auto-routing GenAI models. The idea: Jev picks the most cost-effective models for your task, balancing speed and quality. All generations made with Higgsfield API.

Higgsfield AI 🧩

59,547 Aufrufe • vor 1 Monat

Jev 🤝 CopilotKit We tested UI rendering side by side to demonstrate how Jev from TypeSafe AI can instantly stream components with GPT-6 Luna. Same prompt, renderer and sample data.

Jev 🤝 CopilotKit We tested UI rendering side by side to demonstrate how Jev from TypeSafe AI can instantly stream components with GPT-6 Luna. Same prompt, renderer and sample data.

CopilotKit🪁

21,708 Aufrufe • vor 1 Monat

Adapt explains why nobody ever does collabs with FaZe Jev “he’s inaccessible” 💔

Adapt explains why nobody ever does collabs with FaZe Jev “he’s inaccessible” 💔

yoxic

4,632,933 Aufrufe • vor 1 Jahr

This is f*ckin awesome. A Stanford team pairs JEV with Claude Code to sort 75 billion data points every 11 minutes. JEV runs a cheap first pass on everything. Claude only gets the hard cases. Faster, cheaper, way less compute burned.

This is f*ckin awesome. A Stanford team pairs JEV with Claude Code to sort 75 billion data points every 11 minutes. JEV runs a cheap first pass on everything. Claude only gets the hard cases. Faster, cheaper, way less compute burned.

kiosa

63,141 Aufrufe • vor 1 Monat

Introducing Jev Plays Minecraft! A 24/7 livestream where Jev attempts to defeat the Ender Dragon, one decision at a time. →

Introducing Jev Plays Minecraft! A 24/7 livestream where Jev attempts to defeat the Ender Dragon, one decision at a time. →

Jarrod Watts

53,558 Aufrufe • vor 1 Monat

Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon.

Found a great production use case for Jev. I used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon.

elvis

17,775 Aufrufe • vor 1 Monat

you can call me crazy but.. it's now obvious: grok bot + jev is going to create more millionaires in 2026 than crypto ever did. idea → grokbot → jev decisions → grokbot execution → $$$$$ don’t scroll past this if it hits your timeline. just send this article to grok bot. connect it to jev. thank me later.

you can call me crazy but.. it's now obvious: grok bot + jev is going to create more millionaires in 2026 than crypto ever did. idea → grokbot → jev decisions → grokbot execution → $$$$$ don’t scroll past this if it hits your timeline. just send this article to grok bot. connect it to jev. thank me later.

rody

182,849 Aufrufe • vor 26 Tagen

Jev by TypeSafe AI is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate against.

Jev by TypeSafe AI is now on OpenRouter, in beta. Jev is a System One model. Instead of generating text, it takes your app's state plus a typed question and returns a typed decision with a probability attached. There is no JSON prompting, parsing layer, and nothing to validate against.

OpenRouter

568,781 Aufrufe • vor 1 Monat

I built a thing using Jev. Have you ever been annoyed by not finding an old Claude Code or Codex chat? => Now you can just describe what it was about and Jev finds it in milliseconds. Open Source:

I built a thing using Jev. Have you ever been annoyed by not finding an old Claude Code or Codex chat? => Now you can just describe what it was about and Jev finds it in milliseconds. Open Source:

Florian S

85,808 Aufrufe • vor 1 Monat