Navigation
Recherche
|
OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs
jeudi 14 août 2025, 01:06 , par Wired: Tech.
The new version of ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent.
https://www.wired.com/story/openai-gpt5-safety/
Voir aussi |
56 sources (32 en français)
Date Actuelle
ven. 5 sept. - 07:02 CEST
|