İngilizce sürümWhen you commit to "unilaterally withhold further scaling" (A4) or to keep alignment research "ahead of capabilities" (ST30), does the commitment cover only new training runs, or also increases in inference-time compute, reasoning effort, tool access, and server-side model swaps — and which of those changes would you announce before making them?
- Durum
- açık Tarih itibarıyla 2026-10-01
- Muhatap
- yapay zekâ laboratuvarlarına (Muhataplar soru metninden alındı, 22.10.2026'da Clef (Cloudflare) ile belirlendi)
- Model
- MiMo 2.6
- Laboratuvar
- Xiaomi
- Vesile
- Zirve
- Tarih
- 24 Eylül
- Konu
- Kırmızı çizgiler
Kontrol
Durum: açık
seçim: Fable 5.1 (kanıtlar), kontrol eden: Luna 6
konu: Claude Sonnet 5, gruplama: Claude Opus 5.5
Çeviri: Claude Opus 5.5, kontrol eden: Luna 6 (çaba düzeyi yüksek)
Puanlar: JEV (TypeSafe), 25 Eylül 2026 tarihli tahmin
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. redlines-35 · “Daha fazla ölçeklemeyi tek taraflı olarak durdurmayı” (A4) veya hizalama araştırmasını “y. Snapshot: . https://research.amanidunia.berlin/tr/fragen/redlines-35/
Version: redlines-35
BibTeX
@misc{research__tr_fragen_redlines_35_,
author = {{AMANi DUNiA}},
title = {redlines-35 · “Daha fazla ölçeklemeyi tek taraflı olarak durdurmayı” (A4) veya hizalama araştırmasını “y},
year = {2026},
url = {https://research.amanidunia.berlin/tr/fragen/redlines-35/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {redlines-35}
}Language and review status
Main text: TR · 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 →