[Feature Request] Allow overridable safety filters for academic research on emergent capabilities of sorting algorithms

Open 💬 0 comments Opened Jul 2, 2026 by guischu09

Bug Description
I am writing a paper about diverse intelligence program (a follow up on Michael Levin work) and this nonsense safeguards is flagging that sorting algorithms emergent capabilities are dangerous for humanity.

Paper: Classical sorting algorithms as a model of
morphogenesis: Self-sorting arrays reveal
unexpected competencies in a minimal
model of basal intelligence

Environment Info

  • Platform: linux
  • Terminal: vscode
  • Version: 2.1.198
  • Feedback ID: cfbe7507-454a-41a1-b8a3-e91eab2ab330

Errors

[]

View original on GitHub ↗