Raphaël Millière @raphaelmilliere.com · Nov 7

The outputs of misaligned LLMs can be unreliable and unsafe for users. Problematic behaviors range from minor annoyances to major concerns, including a few high-profile cases of incitation to violent (self-)harm. 4/

0 likes 1 replies

?

Replies

Raphaël Millière · Nov 7

Misaligned LLMs can also be exploited by bad actors for malicious purposes, from misinformation to information hazards. The latter encompass concerns about soliciting dangerous information to cause harm, such as instructions for viral pathogenesis. 5/