▲ 221 ▼ Google Translate is vulnerable to prompt injection (www.greaterwrong.com) submitted 9 months ago by Beep@lemmus.org to c/technology@lemmy.world 34 comments fedilink hide all child comments
▲ 5 ▼ Prompt injection in Google Translate reveals base model behaviors behind task-specific fine-tuning (www.greaterwrong.com) submitted 9 months ago by m_f@discuss.online to c/discuss@discuss.online 2 comments fedilink hide all child comments