Target: persona-nuance goal, corpus golf loop, conlangs in scope
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
parent
adb3615298
commit
2cea2b8a6d
1 changed files with 22 additions and 4 deletions
|
|
@ -3,7 +3,23 @@
|
|||
Campaign `weksa-lowering` (Eureka mind). Operator, 2026-10-29: "having agents
|
||||
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
|
||||
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
|
||||
|
||||
|
|
@ -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
|
||||
from the target profile, never from the lowerer's defaults.
|
||||
- `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)
|
||||
|
||||
- First reader: whose display text is lowered first.
|
||||
- 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
|
||||
|
||||
- Weksa's conlang engine (grammar, phonology, diachrony for alien languages).
|
||||
- MiMo TTS beyond keeping its command working or parking it.
|
||||
- Her Persona's mind; that is `eureka-body:follow_up:weksa-mind`.
|
||||
|
|
|
|||
Loading…
Reference in a new issue