Hovhannes Grigoryan

Tag: alignment

2 items with this tag.

  • Sep 19, 2026

    Steering vectors as a control surface for LLM agents: what reinforcement learning adds

    • agents
    • representation-engineering
    • reinforcement-learning
    • alignment
    • interpretability
  • Mar 01, 2026

    The alignment problem: formal statements and honest limits

    • alignment
    • ai-safety
    • mesa-optimization

Created with Quartz v1.0.0 © 2026

  • GitHub
  • LinkedIn
  • Old site (2019 archive)