Blog

Featured posts

More Capable Models Are Better At In-Context Scheming

We evaluate models for in-context scheming using the suite of evals presented in our in-context scheming paper (released December 2024) with the most capable new models.

19/06/2025
Read more

An Overview Of Our Current Governance Efforts

The governance team at Apollo Research conducts technical governance research, develops tailored policy recommendations, and communicates our organisation’s learnings to key stakeholders across industry, civil society and governments.

21/07/2025
Read more

Forecasting Frontier Language Model Agent Capabilities

We present a new forecasting technique to predict frontier LM agent capabilities ahead of time.

24/02/2025
Read more
All posts
Filter
  • Select all
  • Evaluations
  • Governance
  • Organisation
Governance

Assurance of Frontier AI Built for National Security

09/10/2025
Read more
Evaluations

Research Note: Our scheming precursor evals had limited predictive power for our in-context scheming evals

03/07/2025
Read more
Evaluations

Claude Sonnet 3.7 (often) knows when it’s in alignment evaluations

17/03/2025
Read more
Evaluations

Demo Example – Scheming Reasoning Evaluations

23/01/2025
Read more
Organisation

Apollo 18-Month Update

13/12/2024
Read more
Organisation

Apollo Is Adopting Inspect

13/11/2024
Read more
Evaluations

The Evals Gap

11/11/2024
Read more
Evaluations

An Opinionated Evals Reading List

15/08/2024
Read more
Governance

Our Current Policy Positions

21/06/2024
Read more
Organisation

The First Year Of Apollo Research

29/05/2024
Read more
Evaluations

Black-Box Access is Insufficient for Rigorous AI Audits

04/04/2024
Read more
Governance

Our Work Advancing Scientific Understanding To Foster An Effective International Evaluation Ecosystem

21/03/2024
Read more
Evaluations

We Need A ‘Science of Evals’

22/01/2024
Read more
Evaluations

A Starter Guide For Evals

08/01/2024
Read more
Organisation

Theories of Change for AI Auditing

13/11/2023
Read more
Governance

Recommendations For The Next Stages Of The Frontier AI Taskforce

11/10/2023
Read more
Governance

The UK AI Safety Summit: Our Recommendations

04/10/2023
Read more
Uncategorized

Understanding strategic deception and deceptive alignment

15/09/2023
Read more