A TRPG-shaped instrument for eliciting ideal preferences — preference-elicitation in a role-play wrapper. Live at reflect.meno.sh.
Status: active · People: Zhonghao He, Tianyi Alex Qiu
Open Problems
- Preference / personality modelling is still a deterministic state machine — no LLM-backed user mental model yet.
- Open-world (“emergent”) generation needs systematic testing for coherence and quality.
- UI/UX: keep explanation text minimal; instrument must not read as a game demo.
Progress
- UI fully redesigned to the meno.sh palette + light/dark toggle (PR #21 merged).
?world=emergentper-session toggle wired to the real LLM open-world generator.- Deployed and serving at reflect.meno.sh;
mechanisms.mdis the authoritative spec.
Codebase
reflection-game
05-21Zhonghao He — web: recolor game UI to meno.sh palette + light/dark toggle05-21Zhonghao He — emergent: wire ?world=emergent to the real LLM generator05-21Zhonghao He — Merge PR #21 — web/ui-redesign
Meeting Notes
- STUB — no Circleback notes linked to this channel yet
Slack Discussion
Channel: project-reflection-game
05-21Tianyi Alex Qiu: MenoClaw, rewrite UI to copy this HTML file (minimal explanation text).05-17Zhonghao He: What we want here: models that learn human theory of mind.
Related
Open problems & progress are MenoClaw’s reading of the project — edit this file to correct them; the markdown is the source of truth.