An Anthropic researcher just gave us a peek at self-improving AI
Executive Summary
Given 10 benchmarks for specific misaligned behaviors, the automated systems were able to improve performance on every single one without degrading overall performance.
You May Also Like
Next Logical Step
Anthropic’s prospectus details losses, growth, and, yes, a warning that its AI could end humanity
In its prospectus, Anthropic just told investors it's losing tens of billions of dollars a year, but also growing like c...