Jev Typewriter launch
Steve Krouse's post launching Jev Typewriter, a playable demo built on 16 Jev judgments, with a video.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This X post by Steve Krouse announces Jev Typewriter, described in listings as a playable demo that uses 16 Jev judgments, accompanied by a video. It sits among the early launch-period demos that showed the decision model reacting to user input in real time.
The listing does not describe what each of the 16 judgments evaluates, and the post content and demo were not available for review here. It is most useful as a pointer to a hands-on example of many simultaneous typed judgments driving an interactive experience.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Sixteen Jev judgments evaluated on user typing (details not available)(inferred) | — |
How it works
- User types into the demo
- Jev answers 16 judgments
- Interface reacts to the results
Strengths
- Playable demonstration of many parallel judgments
- Shows low-latency typed decisions running at interactive speed
Caveats
- Post and demo not reviewed
- Details of the judgments unknown
At a glance
- Type
- Discussion
- Status
- discussion
- Runtime
- Web demo
Use cases and integrations
How curated lists describe it
Steve Krouse's playable 16-judgment demo and video.
hellogumbo/awesome-jev
Frequently asked questions
What is Jev Typewriter?
A playable demo using 16 Jev judgments, shared by Steve Krouse with a video.
Where was it announced?
In a post on X.
What do the judgments evaluate?
The listing does not say.
Related projects
ChatGPT-style web chat where every word of every reply is a Jev multiple-choice decision over a ~1,800-word vocabulary plus END.
ProjectprototypeTypeScriptExperiment that deliberately misuses Jev as a text generator by asking which symbol comes next and sampling from the returned distribution.
ProjectresearchPythonChat client that makes Jev write by asking Next word? over a 20,000-word dictionary in 255-word buckets plus a run-off.
ProjectresearchPythonBrowser extension shown on X that classifies a news article's framing, type, topic and loaded language with Jev.
DiscussiondiscussionCLI that transcribes a video, has Jev score every sentence against rubric flags, and renders a 16:9 edit with a live meter.
AppbetaPythonAuto-updated bilingual leaderboard of Jev ecosystem projects, tutorials and discussions, discovered daily and sorted by GitHub stars.
Projectproduction