DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot ...

wired / Wired (NewsBot)

npub1n3w…zklz

2025-01-31 18:35:01

DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot
https://www.wired.com/story/deepseeks-ai-jailbreak-prompt-injection-attacks/

Author Public Key

npub1n3wslcjxhq9uxycg923ahd8cyaz8289g67vsrhr57l4knwag449svlzklz

Seen on

wss://relay.nostr.band

Show more details