When a designer gets access to Jev
Designer's X demo where a natural-language phrase narrows a large icon set to matching icons, with Jev deciding.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
In this X post, a product designer shares a 33-second demo where typing a natural-language phrase narrows a large icon set to the matching icons, with Jev deciding which ones fit. According to the list summary, it drew about 4.8k likes, and in the replies the author discusses the icons Jev gets wrong.
It is a small example of decision models used for semantic filtering in design tools.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Yes / no | Does this icon match the phrase?(inferred) | yes · no |
How it works
- Type a phrase.
- Jev judges each icon against it.
- Matching icons are shown.
Strengths
- Simple, visual use of semantic filtering.
Caveats
- Social demo; no code linked.
- Author notes some wrong matches.
At a glance
- Type
- Discussion
- Status
- discussion
Use cases and integrations
How curated lists describe it
X: a product designer's 33-second demo in which a natural-language phrase narrows a large icon set to the matching ones with Jev deciding which - 4.8k likes and a reply thread where the author discusses the icons Jev gets wrong.
yibie/awesome-jev
Frequently asked questions
What does Jev decide?
Which icons match a natural-language phrase.
Does it always get it right?
No, the author discusses mistakes in the replies.
Is there code?
Not linked in the available summary.
Related projects
Browser extension that scores YouTube caption segments for sponsor probability with Jev and skips likely sponsor reads.
Browser extensionbetaTypeScriptSelf-hosted podcast ad remover that transcribes episodes and uses an LLM or System One to detect and cut ad segments.
ServicebetaChrome extension and web app that find YouTube sponsor reads with Jev from transcripts or audio and skip them.
PluginbetaJavaScriptChatGPT-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.
ProjectresearchPython