HomeAI · summaries
Storia in 5 fonti
La IA que actúa como un hacker: OpenAI desarrolló GPT-Red para romper la seguridad de sus sistemas
La herramienta está encargada de simular ataques informáticos reales para detectar debilidades y corregirlas antes de que puedan ser explotadas.
Confronto fonti
5 prospettive sulla stessa storiaTimeline cronologica
- ·
thenextweb.com
OpenAI built GPT-Red to hack its own AI, and hid it
OpenAI built GPT-Red, an in-house AI hacker that attacks its own models to harden GPT-5.6 against prompt injection, and it works too well to release.
- ·
siliconangle.com
OpenAI details GPT-Red, an AI that attacks its own models to find flaws - SiliconANGLE
OpenAI details GPT-Red, an AI that attacks its own models to find flaws - SiliconANGLE
