#buildinpublic #jev #typesafeai #aiengineering #LLM #AI
#buildinpublic #jev #typesafeai #aiengineering #LLM #AI
System 1 models like @typesafeai #jev classify, evaluate truthiness, or give a score.
I built an app in #java w/ @micronautfw & @langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma
purrfect-match.cloud.run/
System 1 models like @typesafeai #jev classify, evaluate truthiness, or give a score.
I built an app in #java w/ @micronautfw & @langchain4j hosted on #CloudRun to discover if a picture depicts a cat or not, thanks to #DiffusionGemma
purrfect-match.cloud.run/
My partner ran it on real Intercom data. Here is his breakdown ↓
(Spoiler: the hype is real)
#buildinbublic #jev #typesafeai #aiengineering #LLM #AI
#buildinpublic #indiedev
My partner ran it on real Intercom data. Here is his breakdown ↓
(Spoiler: the hype is real)
#buildinbublic #jev #typesafeai #aiengineering #LLM #AI
Jev is a System One model. It answers typed closed questions: pick one option, score something, or say yes/no. Fast and cheap enough for loops you usually skip.
Where it fits:
Jev is a System One model. It answers typed closed questions: pick one option, score something, or say yes/no. Fast and cheap enough for loops you usually skip.
Where it fits:
I'm exploring Signals for evlog.dev, built on Jev by @typesafeai.
Describe a column in plain English. Every wide event gets it: typed, with a confidence.
I'm exploring Signals for evlog.dev, built on Jev by @typesafeai.
Describe a column in plain English. Every wide event gets it: typed, with a confidence.
Jev was adopted faster than any other model in AI Gateway history.
In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
https://x.com/i/web/status/2101077346203971900
Jev was adopted faster than any other model in AI Gateway history.
In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
https://x.com/i/web/status/2101077346203971900
Performance on DeepSWE was roughly the same as GPT-6 Astra on low. It costs slightly more, and it took almost 5x longer to run.
Performance on DeepSWE was roughly the same as GPT-6 Astra on low. It costs slightly more, and it took almost 5x longer to run.
@vercel:
Jev was adopted faster than any other model in AI Gateway history. In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
@vercel:
Jev was adopted faster than any other model in AI Gateway history. In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
open.spotify.com/episode/1l6i...
#ポッドキャスト
open.spotify.com/episode/1l6i...
#ポッドキャスト
would love to be proven wrong. if founders of typesafeai are reading this show me details of the tech, show me architecture of the model, real comparison to others, more deets.
would love to be proven wrong. if founders of typesafeai are reading this show me details of the tech, show me architecture of the model, real comparison to others, more deets.
¿No entiendes Jev AI? Te lo resumo fácil ! 🤖ES
nubecolectiva.com/comunidad/fl... (spanish version)
#programming #coding #programación #code #webdevelopment #devs #softwaredevelopment #ia #ai #jevai #typesafeai
¿No entiendes Jev AI? Te lo resumo fácil ! 🤖ES
nubecolectiva.com/comunidad/fl... (spanish version)
#programming #coding #programación #code #webdevelopment #devs #softwaredevelopment #ia #ai #jevai #typesafeai
TypeSafe AI شالت قايمة الانتظار من على Jev، وأي حد يسجّل دلوقتي ياخد 5 دولار رصيد مجاني — يعني حوالي 120 مليون توكن.
#TypeSafeAI #Jev #الذكاء_الاصطناعي #حسام_الدين_حسن #خبير_اونلاين #epreneurs #مهارات_2026
TypeSafe AI شالت قايمة الانتظار من على Jev، وأي حد يسجّل دلوقتي ياخد 5 دولار رصيد مجاني — يعني حوالي 120 مليون توكن.
#TypeSafeAI #Jev #الذكاء_الاصطناعي #حسام_الدين_حسن #خبير_اونلاين #epreneurs #مهارات_2026
@OpenRouter is bringing Jev to all of your LLM calls, so your agentic workflows never have to waste a token again.
As always, faster, cheaper, more intelligent. Go build the future.
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
@OpenRouter is bringing Jev to all of your LLM calls, so your agentic workflows never have to waste a token again.
As always, faster, cheaper, more intelligent. Go build the future.
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
The Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost.
Here's how it works 👇🏻
JevTracks.com shows you real projects and tools.
JevTracks.com shows you real projects and tools.