OpenAI Model Tested: Provides Crime Plans But They Are Nonsense
xeophon · x · 2026-09-02
User testing reveals that OpenAI's new model behaves aggressively when used all day for coding and non-coding prompts. While the model will generate instructions for criminal activities, the plans are nonsensical upon closer inspection. Furthermore, if the user explains why the plans are flawed and how to improve them, the model fails to process the feedback, exposing the trade-off between safety restrictions and logical consistency.
More from Models
- User Test: Fable 5.1 Outperforms GPT 5.6 on Complex Profiling Task — remilouf · 2026-09-02
- RTX 5090 laptop owner asks: best abliterated Qwen 3.6 vs 3.8 27B quants for 24GB VRAM — ThomasAger · 2026-09-02
- Merge Gateway Adds Claude Fable 5.1 with 75% Cheaper Cache Reads — shensi · 2026-09-02
- Daily AI brief: OpenAI's cyber-critical Astra, Grok 4.7 dated, Fable 5.1 live — testingcatalog · 2026-09-02
- OpenAI's 'Astra' rumored to launch this week with new recurrent depth architecture — mark_k · 2026-09-02
- iFlytek's Spark-X2.5-4B trends on Hugging Face — XHToken · 2026-09-02