Re:LLMs are too easy to automatically red team into toxicity
by lcnPylGDnU4H9OF on Monday July 03, 2023 @06:35PM
(#36579699)
It’s an information security “penetration testing” reference. Red Team is trying to “attack” some other Blue Team.
The meaning seems to be that an LLM can have certain vulnerabilities exploited (“red teamed”) such that it exhibits behaviors that its training algorithm had intended it to avoid.
The meaning seems to be that an LLM can have certain vulnerabilities exploited (“red teamed”) such that it exhibits behaviors that its training algorithm had intended it to avoid.