Jev organized 2.3K research papers for 14 cents
X post reporting that Jev sorted about 2,300 AI research papers in roughly 83 seconds for $0.14 in total.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This entry is an X post describing a production-style use of Jev: sorting roughly 2,300 AI research papers into categories. According to the list summary, the run took about 83 seconds and cost $0.14 in total.
It is a data point on cost and throughput for bulk classification with a decision model. No further details such as the category scheme or accuracy checks were available.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which category does this research paper belong to?(inferred) | — |
How it works
- Collect paper metadata or abstracts
- Ask Jev a category Choice per paper
- Group papers by the returned category
Strengths
- Reported low total cost and fast throughput for 2,300 items
Caveats
- No accuracy figures in the summary
- Post only; methodology not captured
At a glance
- Type
- Discussion
- Status
- discussion
Use cases and integrations
How curated lists describe it
X: a production use case reporting that sorting roughly 2,300 AI research papers took about 83 seconds and cost $0.14 in total.
yibie/awesome-jev
Frequently asked questions
What was reported?
Sorting about 2,300 AI research papers in roughly 83 seconds for $0.14.
Was accuracy measured?
The summary does not say.
Where was it posted?
On X.
Related projects
Hacker News thread where a builder claims prior open-sourced work on the same non-autoregressive decision architecture as Jev.
DiscussiondiscussionBilingual catalogue of Jev papers, software projects and public materials, with evidence levels, published as a static site.
AppproductionAuto-updated bilingual leaderboard of Jev ecosystem projects, tutorials and discussions, discovered daily and sorted by GitHub stars.
ProjectproductionChatGPT-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