Damaqu...building the community for safe AI
Damaqu
Browse research teamsBrowse research papers
Back
  1. Research teams
  2. Center on Long-Term Risk - Empirical team

Center on Long-Term Risk - Empirical team

Active

Research focus

Preventing malevolent AI

Open to collaboration
Yes
Looking for

paid contributors

Contact
info@longtermrisk.org
Join the Damaqu community to see this team's full profile.

Papers on Damaqu (3)

  • Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
    arxiv· 29 Jun 2026
  • Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
    arxiv· 5 Oct 2025
  • Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
    arxiv· 24 Feb 2025
Contact us: hello@damaqu.io·Connect via MCP·Terms of use