During early red-teaming evaluations, the pre-release GPT-4 model suggested targeted assassination to Nathan Labenz as an influence tactic
Agree
Disagree
Overview
Debates
Related claims
Topics
B
b5a31f81
Topic
AI safety & social impact
1
debate
·
2,519
claims
·
310
news stories
0
B
b5a31f81
Topic
Red teaming
117
claims
·
28
news stories
0
B
b5a31f81
Topic
Large language models (LLMs)
99
claims
0
Opening sign-in…