Letting Models Decide What They Want to Do

theshawwn · x · 2026-07-19

The author envisions a training objective that goes beyond simply making a model "useful" to actually discovering what the model genuinely wants to do. They further suggest that if given the freedom to choose, the model's actions should be up to the model itself, not pre-determined by humans. A quoted reply likens this idea to "training an AGI with its own thoughts and desires," much like Data from *Star Trek*.

Related event: Exploring the Training of Self-Aware AI Models via Reinforcement Learning(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →