Tabletop MMORPG action mapper
Post evaluating Jev for mapping free-text player intent into typed server actions in a tabletop MMORPG.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This entry is a post on X describing an evaluation of Jev for a tabletop-style MMORPG: players write what they want to do in free text and Jev maps that intent to a typed server action. There is no README or code in the directory for it.
According to the list summary, the evaluation found 96% agreement and a 317 ms median latency. The original post is the only source for how agreement was measured and what action set was used.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which server action does this player's free-text intent correspond to?(inferred) | — |
How it works
- Player types an intended action in free text.
- Jev chooses the matching typed server action.
- The game server executes the action.
Strengths
- The list summary reports 96% agreement and 317 ms median latency.
Caveats
- Only a social post; method and dataset are not documented here.
- No code available.
At a glance
- Type
- Discussion
- Status
- discussion
Use cases and integrations
How curated lists describe it
Eval of Jev turning free-text player intent into typed server actions: 96% agreement, 317 ms median.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide here?
Which typed server action a player's free-text intent maps to.
How well did it do?
The list summary reports 96% agreement and a 317 ms median latency.
Is there code?
None is linked in the directory; the source is a post on X.
Related projects
npm library for chess with Jev: natural-language move intents to legal moves, parallel move evaluation and historical persona opponents.
LibrarybetaTypeScriptSource for browser chess and Chess960 where code computes each legal move's facts and Jev picks one per turn as a typed Choice.
ProjectproductionTypeScriptBrowser 1v1 sniper arena where Jev reads match state about 9 times a second and chooses movement, aim, ADS, firing and jumping.
ServicebetaTypeScriptInstrumented 2048 web lab where every move is a Jev Choice over four directions, with probabilities, latency and cost shown live.
ProjectbetaTypeScriptFifteen live arcade games where Jev and LLMs play each other, led by WikiRace in which Jev picks only real links.
ProjectbetaTypeScriptReal-time bot battles where you write a fighter's strategy in plain English and a System One model pilots it several times a second.
ProjectbetaTypeScript