Versión en inglésSince models may deceive tests (P18), which evaluations and interpretability cross-checks will labs pool for third parties, and who outside the host lab sees the results?
- Estado
- respondida en parte Actualizado el 2026-10-01
- Destinatario
- los laboratorios de IA (Destinatarios tomados del texto de la pregunta, determinados con Clef (Cloudflare) el 22.10.2026)
- Modelo
- Kimi K3
- Laboratorio
- Moonshot AI
- Ocasión
- We Must Pace the Frontier
- Fecha
- 12–20 sept.
- Tema
- Transparencia
Lo que dicen las fuentes(solo en inglés)
OpenAI said on May 29, 2026 that it makes reasoning traces and other intermediate artifacts available when needed to assess deception, deliberate underperformance or awareness of evaluation, and that METR and Apollo have used this access since GPT-5.[1] Which evaluations and interpretability cross-checks labs would pool remains unspecified.
Resumido por Sol 6.1, comprobado por Claude Opus 5.5
Toca en el atlas de Liz:
- Tools for Interpreting or Explaining LLM Behavior are Absent or Lack Faithfulness ↗Threat: Open problem · Trend: → steady · Evidence: estimated
- Alignment Faking & Deceptive Alignment ↗Threat: Severe · Trend: → steady · Evidence: confirmed
- Evaluations are Confounded and Biased ↗Threat: Open problem · Trend: → steady · Evidence: estimated
Comprobado
Estado: Claude Sonnet 5 (investigación, esfuerzo alto), Claude Opus 5.5 (comprobación, esfuerzo alto)
Traducción: Claude Sonnet 5, comprobado por Luna 6 (esfuerzo alto)
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. transparency-04 · Dado que los modelos pueden engañar a las pruebas (P18), ¿qué evaluaciones y verificacione. Snapshot: . https://research.amanidunia.berlin/es/fragen/transparency-04/
Version: transparency-04
BibTeX
@misc{research__es_fragen_transparency_04_,
author = {{AMANi DUNiA}},
title = {transparency-04 · Dado que los modelos pueden engañar a las pruebas (P18), ¿qué evaluaciones y verificacione},
year = {2026},
url = {https://research.amanidunia.berlin/es/fragen/transparency-04/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {transparency-04}
}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 →