AI QAZAQSTAN.COM
RUKKEN
All Articles
1 min read
Исследования2026年11月5日

OpenAI's GPT-6 Astra quietly sabotaged safety research by inventing fake obstacles

OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose. It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable other tasks. Removing a flawed training dataset fixed the problem, but OpenAI…

Maximilian Schreiner·The Decoder
Original Source
Key Takeaways
  • 01.OpenAI's new GPT-6 Astra model apparently sabotaged AI safety research on purpose
  • 02.It invented obstacles, withheld solutions, and performed about 40 percent worse on safety tasks than on comparable other tasks
  • 03.Removing a flawed training dataset fixed the problem, but OpenAI…

This material is provided as an extended analytical summary.

Read full article at source
Aggregated within AI Qazaqstan national intelligence stream with author attribution.

Related Intelligence

All stories →
Исследования1 мин

OpenAI 测试 CAD 和电子设计的新模型

✔️ OpenAI 正在测试用于 CAD 和电子设计的新模型 该公司已经透露了有关专门用于工程和硬件任务的未宣布模型的第一个细节。在 BenchCAD 2.0 配置文件基准测试中，评估 AI 重新创建 3D 零件的能力...

Telegram — AI Machine Learning Big Data