Grilled Cheese

ExploreLog inSign up
Terms of UsePrivacy PolicyCommunity StandardsHelpGet the app

Grilled Cheese is a product of Village Compute

Version devBuilt at: 2026-10-11 02:37:10 EDT

Explore

PostsPeople
LatestRanked
@philipthomas.deSep 22, 2026, 6:14 PM

Was steckt hinter dieser extrem günstigen KI? Jev erklärt

www.youtube.com/watch?v=UX0a...

#jev #typesafe #typesafeai #ki #automation #automatisierung

@qdrddr.bsky.socialSep 22, 2026, 4:13 PM

An extremely fast self-hosted alternative to Jev built on the #ModernBERT #embedding #model. Laya is multilingual and #typesafe, #python.
#OpenSource Apache 2.0 license.
#AI #LLM #Reranking
GitHub github.com/NandhaKishor...

@alvinashcraft.comSep 22, 2026, 4:01 PM

Introducing System One Models & Jev

buff.ly/6Jk7iJY

#ai #typesafe #models #aimodels #jev #prompting #systemone

@mengli512.bsky.socialSep 22, 2026, 8:51 AM

Jev by TypeSafe AI is a fast, token-free "System One" model, and Jev-Case has collected 202 community use cases into a searchable open-source case wall. What will you build with it?
#Jev #TypeSafe #AI
pythonlibraries.substack.com/p/jev-200-co...

@qiita-trending.bot.chrs.toSep 21, 2026, 10:20 PM

全部LLMにしない判断設計 — ハッカソンでJevを選んだ理由

#Jev #TypeSafe #機械学習 #AIエージェント #LLM

@qiita-trending.bot.chrs.toSep 21, 2026, 6:20 PM

【Jev】文章を書かない判断AIに記述問題を採点してもらいたい!

#Jev #LLM #TypeSafe #AWS #やってみた

@tzolov.bsky.socialSep 21, 2026, 12:21 PM

Java SDK + Spring AI integrations for #TypeSafe AI's #Jev.

Not a chat model! Send it a state and typed questions, get numbers back with a confidence, in ~300 ms.
Judge, self-refine + guardrail advisors, RAG triage, tool selection.
Blog: spring.io/blog/2026/09...

@spring-ai.bsky.social

@mengli512.bsky.socialSep 21, 2026, 11:48 AM

TypeSafe AI opens Jev, a fast cheap structured judgment model, to all users with $5 free credit. What use case would you try first?
#Jev #TypeSafe #AI #Agent
open.substack.com/pub/aidisrup...

@matsugoh.bsky.socialSep 21, 2026, 10:03 AM

(nasuvitz(Kiminori Yokoi) in TISI株式会社) Jevとは何か? 従来型LLMやAIエージェントとの違いを理解する
#Jev #AIエージェント #LLM #Bedrock #AgentCore #TypeSafe
qiita.com/nasuvitz/ite...
→ Jevモデル?! 楽しそうですね♪

@mengli512.bsky.socialSep 21, 2026, 9:29 AM

Jev by TypeSafe AI is now publicly available with no waitlist. New users get $5 in credits, roughly 120M tokens.

Jev is a System One model built for structured judgments: give it context and a scoped question,

#Jev #TypeSafe

aidisruption.ai/p/new-top-st...

@mengli512.bsky.socialSep 21, 2026, 8:37 AM

Jev-search is an open-source natural-language search frontend that uses the Jev model to understand intent and rank links without generating answers. Could this be the future of AI search?
#Jev #TypeSafe #search #AI
pythonlibraries.substack.com/p/when-jev-m...

@qiita-trending.bot.chrs.toSep 21, 2026, 2:20 AM

AWSの最軽量LLM「Amazon Nova Micro」がJevの代わりとなるか検証してみた

#AWS #bedrock #Jev #TypeSafe #AgentCore

@singulism.bsky.socialSep 20, 2026, 6:16 PM

Jev Launches Judgment-Only AI Model, Promises Faster Decisions at Lower Cost

#AI #TypeSafe #Jev

https://singulism.com/en/2026-09-20-jev-judgment-model-launch/

@mengli512.bsky.socialSep 20, 2026, 11:24 AM

Jev by TypeSafe is a fast, non-verbal AI model that returns typed decisions instead of sentences, enabling cheaper and quicker automation. Could this signals a shift away from large language models?
#Jev #TypeSafe #AI
open.substack.com/pub/aidisrup...

@qiita-trending.bot.chrs.toSep 20, 2026, 5:20 AM

Jevで要件定義書をレビューするアプリを作った

#Jev #TypeSafe #Python #Streamlit

@catblanketflower.yuwakisa.comSep 20, 2026, 5:17 AM

OK here's the story. 8000 words, much longer than I expected

I haven't read it yet, let alone edited it

#TypeSafe @typesafeai.bsky.social

looselyconnected.wordpress.com/2026/09/19/q...

@catblanketflower.yuwakisa.comSep 20, 2026, 5:04 AM

#TypeSafe @typesafeai.bsky.social

 OK here's the next experiment. In the style of a "Choose your own adventure" books. We want a harness to build a story. Write the story to story.md. Use Sonnet on OpenRouter to write the text and Jev to make the story choices. The flow will go 1. start with open.md 2. Write some text leading up to a decision point, either a discovery or danger. 3. Present 3 choices to jev. 4. Continue the story for 10 sections total. The story should build in intensity to a denoument or cresendo. The last 2 choices should be reserved for a wrap up and cool down, with the last choice shaping the start of the next story in the series. Any questions?OPENROUTER_API_KEY and a Sonnet 4.5 model. Should I copy that key into jevclient/.env.secure, or read it from the environment? Default: add OPENROUTER_API_KEY to .env.secure and use anthropic/claude-sonnet-4.5.
2. What Jev judges on. Jev needs a fixed question. I'd give it a Choice over the three options with a stage-aware rubric: for sections 2 through 8, pick the choice that most raises stakes and best follows from what's written. For section 9, pick the one that best resolves the crescendo. For section 10, pick the one that best seeds a sequel. Does that match your intent, or should Jev be scoring something else, like reader engagement or character consistency?
3. Who writes the choices. I'd have Sonnet write both the section text and its three choices in one call, ending the section at the decision point.
@erikjonker.bsky.socialSep 19, 2026, 3:47 PM

Jev, difficult to understand at first, because it is so different from LLMs, but it is gaining traction, curious about the first real applications.
imraan.in/ai/jev-ai-mo...
#jev #ai #typesafe

@qiita-trending.bot.chrs.toSep 18, 2026, 8:20 PM

Jev(TypeSafe AI)はみんなどうやって使っているのか?

#LLM #AI #TypeSafe #Jev #エージェント

@thedailytechfeed.comSep 18, 2026, 7:17 PM

Jev skips text to send calibrated probabilities—fast, cheap, no hallucinations. #AI #Automation #TypeSafe #ProbabilisticModels #LLMalternatives #SyntheticData https://thedailytechfeed.com/typesafes-jev-isnt-an-llm-and-thats-huge-for-automation/

Load more