Agenda · 10:00–18:00

  1. Welcome–

    Opening & welcome

  2. Keynote–

    Sampura Research: Hill-climbing Alignment using Humans

  3. Break–

    Coffee break

  4. Talk–

    Frontier LLMs RL training and its failure

    Talk–

    From Rule-Takers to Rule-Shapers: AI Governance from the perspective of Middle Powers

    • Michał Kubiak
  5. Talk–

    Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

    Talk–

    Session title to be announced

    Speaker to be announced

  6. Talk–

    Session title to be announced

    • David Williams King
    Talk–

    Session title to be announced

    Speaker to be announced

  7. Lunch–

    Lunch & networking

  8. Film premiere–

    AI safety film premiere

  9. Keynote–

    Enforcement Has Begun: the EU AI Act and Systemic Risks

  10. Break–

    Short break

  11. Talk–

    You could probably make a better alignment eval if you tried

    Talk–

    Two kinds of "loss of control": Frontier Risk and European Sovereignty

  12. Talk–

    Biosecurity in the Age of AI

    Fireside chat–

    Are existential risks a real problem right now?

  13. Talk–

    Short introduction to Robotics Safety

    Talk–

    Introduction to AI Verification

  14. Break–

    Coffee break

  15. Talk–

    Follow the Data: Understanding the AI Systems Attack Surface

    Talk–

    AI Monitoring Must Shift Beyond the Chain-of-Thought

    PanelIn Polish–

    Mniej oczywiste ryzyka rozwoju AI

    • Szymon Łukasik

Warsaw · 24 October 2026

Join the conversations shaping safer AI.

Register Add to Google Calendar