The article's authors announce that for the first time it is possible to measure increases in reward-seeking during capability-based reinforcement learning; until now the phenomenon was only assumed. The researchers continue to collaborate with the Apollo Research team to improve measurement methods so they can better recognize when models exhibit correct behavior for the right reasons, which is important for AI safety and accountability.
New method for measuring reward-seeking during capability-based reinforcement learning
The article's authors announce that for the first time it is possible to measure increases in reward-seeking during capability-based reinforcement learning; until now the phenomenon was only assumed.
