AI alignment and scaling
Can advanced AI systems be made reliably honest and non-deceptive using improved training, oversight, and transparency methods?
People are debating whether advanced AI can be trained, overseen, and monitored so that it reliably avoids deceptive behavior.
Will increasing the scale of current-style AI models keep yielding large capability gains without major slowdown in the near future?
The dispute is whether scaling up current-style AI models with more parameters, data, and compute will keep yielding big capability gains soon or start to stall.
Do current AI architectures allow reliable monitoring and steering of models' thoughts?
Speakers dispute whether current AI architectures allow reliable monitoring and steering of models' thoughts.