What it does
A public replay plots saved judgments without calling either model; the live-conference path uses providers. The model judges the captioned words, not the market’s reaction.
Apps & data pipelines
Jev vs Chat Model: Hawk or Dove?
Watch Jev and a chat model judge a Fed chair’s remarks as hawkish or dovish, line by line.
Bookmark: Jev vs Chat Model: Hawk or Dove?
Keep this in your collection.
Leave a noteWhat would you try with this?
: Jev vs Chat Model: Hawk or Dove?
Only you can see your notes.
Recording unavailable. Open the experiment ↗
How you can use it
You can build an app that compares how two different AI systems rate spoken statements. Start by gathering speech transcripts or captions and defining the specific stances you want to test. Have a developer build a server that sends each line to both models and plots their answers side by side.
Watching saved sample replays works without connecting to paid services. To evaluate fresh remarks or live conferences, your developer must connect provider accounts using an access key. Keep in mind that these models evaluate the speaker's exact words, not real-world market movements.