Designing AI agents to resist prompt injection
March 11, 20260 views1 min read
How ChatGPT defends against prompt injection and social engineering by constraining risky actions and protecting sensitive data in agent workflows.
Share:
Источник: OpenAI Blog
Related News
AI
Neural NetworksOpenAI Releases GPT-5
OpenAI released GPT-5, a new AI model with improved capabilities in text generation, mathematics, and programming.
5h ago66
AI
Neural NetworksCursor capitalizes on GitHub frustration, launches rival hosting platform
6h ago17
Neural NetworksRobin Williams’ Instagram account brought back to fight ‘AI abuse’
8h ago12