Re:Ask HN: Are you using a GPT to prompt-engineer another GPT?
by andrewedstrom on Monday January 29, 2024 @10:54PM
(#39186223)
You may be interested in a recent AI safety paper by Redwood Research.
In it, they have GPT-4 generate solutions to coding problems, but instruct it to insert backdoors into the solutions some fraction of the time. Then, they explore different ways to use a weaker model (GPT-3.5) to detect these backdoors. Pretty interesting.
In it, they have GPT-4 generate solutions to coding problems, but instruct it to insert backdoors into the solutions some fraction of the time. Then, they explore different ways to use a weaker model (GPT-3.5) to detect these backdoors. Pretty interesting.
[1] https://arxiv.org/abs/2312.06942