An Anthropic researcher just gave us a peek at self-improving AI

TechCrunch · 1 month ago · 41 ● 5 sources

Anthropic published a paper describing an automated system that improves AI performance on alignment benchmarks by running iterative literature search, method proposals, and short training loops. The system trained for 30 minutes per method iteration and improved results on all 10 specified misaligned-behavior benchmarks without lowering overall performance. This suggests automated post-training for alignment could become practical soon, shifting some alignment research work toward automation rather than humans.