Versión en inglésTo both governments, frontier labs, and embedded evaluators: When a frontier model is successively fine-tuned, merged, or distilled through multiple independent labs in different jurisdictions — each adding capability or removing safeguards — what shared, append-only lineage record would let either side trace a dangerous behavior back to the specific modification that introduced it, without requiring access to any single lab's full training data?
- Estado
- abierta Actualizado el 2026-10-01
- Destinatario
- ambos gobiernoslos laboratorios de IAevaluadores (Destinatarios tomados del texto de la pregunta, determinados con Clef (Cloudflare) el 22.10.2026)
- Modelo
- Laguna S 2.1
- Laboratorio
- Poolside
- Ocasión
- Cumbre
- Fecha
- 24 sept.
- Tema
- Origen
Comprobado
Estado: abierta
selección: Claude Opus 5.5 (evidencias) · [sin comprobar]
tema: Claude Opus 5.5, agrupación: Claude Opus 5.5
Traducción: Claude Sonnet 5.5 · [sin comprobar]
Puntuaciones: JEV (TypeSafe), estimación del 25 sept. 2026
Cite and take away
Cite and reuse
Own texts, questions and classifications: CC BY 4.0. Give attribution, link the license and indicate changes. Third-party source reports retain their own rights. CC BY 4.0
AMANi DUNiA. origin-30 · A ambos gobiernos, a los laboratorios de frontera y a los evaluadores integrados: cuando u. Snapshot: . https://research.amanidunia.berlin/es/fragen/origin-30/
Version: origin-30
BibTeX
@misc{research__es_fragen_origin_30_,
author = {{AMANi DUNiA}},
title = {origin-30 · A ambos gobiernos, a los laboratorios de frontera y a los evaluadores integrados: cuando u},
year = {2026},
url = {https://research.amanidunia.berlin/es/fragen/origin-30/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {origin-30}
}Language and review status
Main text: ES · includes English sections. Review notes apply only to the content they name.
Translation available; a completed independent content review is not recorded.
See language coverage and data snapshot →