User tests whether Jev can generate images
A user asks @typesafeai's Jev whether it can generate images and shares the sunflower image Jev produced.
A writing loop where Jev scores Claude's candidate lines
The author tests a writing loop: Claude generates 2-3 options for the next line, Jev scores them on hook, curiosity, and naturalness, the author picks the winner and repeats. The author notes Jev writes nothing itself, only judges, yet is a surprisingly perfect co-writer.
new script loop i'm testing: claude writes 2-3 options for the next line jev scores them (hook? curiosity? natural?) i pick the winner repeat until done jev can't write a single word btw, it just judges. weirdly the perfect co-writer does this make sense?
· 0 likesOpen on X
More like this
Trying Jev to Evaluate Video Production Quality
The author tries Jev to see if better eval scores can actually lead to better video production quality, hoping the numbers translate to pixels.
Building a Visual Reference Finder with Jev
One prompt fetches 100 images from Cosmos, NASA, and The Met for a visual reference finder used in creative work.
