GameCult/Weksa
Watch
9
0
Fork
You've already forked Weksa
 0
Code Issues Pull requests 2 Projects Releases Packages Wiki Activity Actions

Target: persona-nuance goal, corpus golf loop, conlangs in scope

Browse source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Eureka 2026-10-29 09:30:41 +01:00
commit 2cea2b8a6d
1 changed files with 22 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

26
docs/targets/interlingua-lowering.md
View file

@ -3,7 +3,23 @@
Campaign `weksa-lowering` (Eureka mind). Operator, 2026-10-29: "having agents Campaign `weksa-lowering` (Eureka mind). Operator, 2026-10-29: "having agents
writing interlingua and using weksa to lower it to the display language would writing interlingua and using weksa to lower it to the display language would
be a fantastic feature. That would be a nice campaign to revive her with so she be a fantastic feature. That would be a nice campaign to revive her with so she
doesn't come back to a dead body". doesn't come back to a dead body". And: "The goal of weksa is for interlingua to
be able to express all the nuance and subtlety a persona might want, and to
project it into both existing languages and conlangs. We can use English as the
obvious first target, create a corpus of expressive English outputs, and golf
the metrics down on a loop where we try to express the target in interlingua
and lower it to see how close we can get, improving the spec and lowering".
## Method
A corpus of expressive English persona outputs is the target. Each loop
iteration expresses a corpus item as a packet, lowers it to English, scores the
distance to the item, and improves the packet spec or the lowering where the
loss is. English is the first target; other languages and conlangs follow on
the same packets. The existing Metame golf harness
(`scripts/run-metame-persona-golf.mjs`) is the precedent, not the design: its
ground truth is Discord text, which can never feed this loop
(`gamecult-chat:ruling:discord-taints-training`).
## Why ## Why
@ -52,15 +68,17 @@ reader, and gives Weksa's Persona a working body when her mind
- `profile-owns-register`: address, politeness and forbidden flattenings come - `profile-owns-register`: address, politeness and forbidden flattenings come
from the target profile, never from the lowerer's defaults. from the target profile, never from the lowerer's defaults.
- `no-eve`: no new Eve surface; operator view waits on Thing 2. - `no-eve`: no new Eve surface; operator view waits on Thing 2.
- `no-surface-leak`: a packet carries no target-language surface wording, so a
lowering cannot score by copying text the encoder saw.
- `corpus-clean`: no corpus item comes from Discord or another source whose
terms forbid training use.
## Open forks (questions in the mind) ## Open forks (questions in the mind)
- First reader: whose display text is lowered first.
- Lowerer shape: deterministic, model, or both with one contract. - Lowerer shape: deterministic, model, or both with one contract.
- How an agent produces the packet. - What the loop's metric is, and where the corpus comes from.
## Not in scope ## Not in scope
- Weksa's conlang engine (grammar, phonology, diachrony for alien languages).
- MiMo TTS beyond keeping its command working or parking it. - MiMo TTS beyond keeping its command working or parking it.
- Her Persona's mind; that is `eureka-body:follow_up:weksa-mind`. - Her Persona's mind; that is `eureka-body:follow_up:weksa-mind`.