"This is a future problem about future models that we don't even know how to design, and certainly don't have access to," says Collin Burns, a member of OpenAI's superalignment team.
"It has been a long-standing challenge to develop good empirical testbeds for the problem of aligning the behavior of superhuman AI systems," he tells IEEE Spectrum. "This paper makes a promising step in that direction and I am excited to see where it leads."
[
add
]
[
|
|
...
]