Quantcast
Channel: BLOCKGENI
Viewing all articles
Browse latest Browse all 374

DeepSeek’s R1 apparently ‘more vulnerable’ to jailbreaking than other AI models

$
0
0

According to The Wall Street Journal, the most recent model from DeepSeek, the Chinese AI firm that has rocked Silicon Valley and Wall Street, can be programmed to generate dangerous content like bioweapon attack plans and a campaign encouraging teen self-harm. According to Sam Rubin, senior vice president of Unit 42, Palo Alto Networks’ threat intelligence and incident response agency…

Source


Viewing all articles
Browse latest Browse all 374

Trending Articles