This is tricky: To do this, we’ll need ways for the human who’s supervising the model to use any relevant knowledge or skills that the model already has, even though they can’t trust the model to be reliably helpful.
AGENTS
-
Scalable Oversight: Supervising AI Systems Beyond Human Capabilities
By
–
To ensure that AI systems remain safe as they start to exceed human capabilities, we’ll need to develop techniques for scalable oversight: the problem of supervising systems’ behavior without assuming that the overseer understands the task better than the system being trained.
-
Y Combinator Offers Funding and Model Access for AI Startups
By
–
we will write you a check, give you preview access to new models, and try to help with ML issues and strategy. YC is YC. you could happily do both!