Hosted on MSN1mon
Researchers say they had a ‘100% attack success rate’ on jailbreak attempts against Chinese AI startup DeepSeekrecipes for chemical concoctions, cybercrime instructions, and content deemed as harassment, harmful, and illegal. “The results were alarming: DeepSeek R1 exhibited a 100% attack success rate ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback