Apollo Research

ResearchFounded 2023 · UK

Visit their site

Evaluate frontier models for deceptive and 'scheming' behaviour and build a science of scheming.

Apollo is a London lab that tests whether AI models will lie, sandbag, or try to evade shutdown. Its findings appear in the labs' own model reports.

Focus

  • Safety evaluations
  • Alignment research

Funding, as far as we know

Philanthropic grants (incl. Open Philanthropy / Coefficient Giving); specifics beyond that unknown

What they've actually done

  • Published 'Frontier Models are Capable of In-context Scheming', showing o1, Claude and others could sabotage oversight in tests

    5 December 2024

    Source

  • Collaborated with OpenAI on 'deliberative alignment' anti-scheming evaluations and training

    17 September 2025

    Source

  • Conducted pre-deployment scheming evaluations cited in OpenAI, Anthropic and Google DeepMind system cards

    2024-2026

    Source

Last verified 1 September 2026

Report a correction

Back to all organizations