Mastodon discussion Discussions 4h ago

https://ai.meta.com/blog/practical-ai-agent-security/ - #Meta discusses securing against #LLM prompt injection. The sess...

by robrich

https://ai.meta.com/blog/practical-ai-agent-security/ - #Meta discusses securing against #LLM prompt injection. The session can include no more than 2 of:[A] process untrustworthy inputs[B] access to sensitive systems or private data[C] can change state or communicate externally

Read Original
LLM

Metadata

Account
robrich@hachyderm.io

Related