Hey Kuyawa, it's not a tool for agentic coding. Have a look at product page: https://typesafe.ai/blog/introducing-system-one-models-and-j.... Use cases: "AI-Powered Workflows / smart if-statements"

Jev does a useful thing, but to me it feels like it should be some middleware plugin available to many AI harnesses, not a standalone product. Under the hood, model tool calls were doing a similar classification to decide if a tool should be called amidst a set of tool descriptions - so for instance, it might be nice plugged into that use if it delivers faster, more accurate tool invocations.

yes. i used it like that. big model is planning - JEV chooses elements on a site to click. i made a super fast mcp browser. JEV got a list & aim and gives back the probabilities - the tool clicks. result: in 6 cases (button, form, dropdown, read table) = 3 secs and 0,02 Cent. Opus did it in 10 sec vor 11 Cent. crazy imho. didn't do heavy tasks though - pity it can't write text. did anyone had a look at laya yet?

I love horseback riding and do it all the time. I can't walk past an open field without wishing my horse Fawkes and I were cantering across it.

So when I heard about Jev, I was pretty excited. But as I learned more, I realized Jev can't ride horses, can't muck a stall, can't teach a flying lead change, and can't even reset a thrown shoe.

Maybe I'm doing it wrong, but I can't figure out why this exciting new thing doesn't work for my personal interest. Its lack of horseback riding support is a dealbreaker for me.