
Institute · London, United Kingdom
Apollo Research
London-based AI safety organisation that evaluates frontier models for scheming and publishes open evaluation and interpretability work.
London, United Kingdom
- Founded
- 2023
- Type
- Institute
- Based in
- London, United Kingdom
- Key papers
- 2
- Featured projects
- 7
About
Apollo Research was founded in 2023 and is led by CEO and co-founder Marius Hobbhahn. Its stated goal is to secure frontier AI systems across development, deployment and governance, with a focus on scheming, where advanced systems covertly pursue misaligned objectives.
In 2023 it presented at the UK AI Safety Summit and advised the Frontier AI Taskforce. In 2024 it tested OpenAI's o1 before release and published early evidence of in-context scheming in frontier models; in 2025 it ran evaluations for major labs and worked with OpenAI on anti-scheming interventions.
In 2026 the organisation became a Public Benefit Corporation, opened a San Francisco office and began building Watcher, an agent monitoring tool. It publishes code on GitHub, including end-to-end sparse dictionary learning.
Mission and ambitionsApollo aims to reduce the risk of deceptive and misaligned AI through evaluations, interpretability research and governance advice. It works with developers and governments.
Known for
- 01
Scheming evaluations of frontier models
- 02
End-to-end sparse autoencoders
- 03
Pre-deployment testing with OpenAI
- 04
Loss of control playbook
Milestones
- 2023
Presented at AI Safety Summit
Apollo identified scheming as a serious risk and presented at the UK AI Safety Summit.
- 2024
End-to-end SAEs
Released training code and weights for end-to-end sparse dictionary learning (arXiv 2405.12241).
- 2024
o1 pre-deployment testing
Partnered with OpenAI to test o1 before public release.
- 2024
In-context scheming evaluations
Published evaluations showing frontier models can scheme in context (arXiv 2412.04984).
- 2025
Anti-scheming work
Partnered with OpenAI on anti-scheming interventions and wrote a loss of control playbook for governments.
- 2026
Public Benefit Corporation
Became a PBC, opened a San Francisco office and began building Watcher.
Open source
Open-source repository. (66 stars)
Open-source repository. (61 stars)
Sparse Autoencoder Training Library (59 stars)
Attribution-based Parameter Decomposition (35 stars)
Model with 4 likes on the Hub.
Model with 1 likes on the Hub.
Dataset with 5 likes on the Hub.
Research papers
Notable releases
Openness
Research code, SAE weights and datasets are public; its evaluations of frontier models are published as papers.
People
- Marius HobbhahnCEO and co-founder
- Chris AkinChief Operating Officer
- Alexander MeinkeHead of Research
- Jérémy ScheurerMember of Technical Staff
- Charlotte StixChief Governance Officer
Listed from the lab's own pages and public profiles.
Contact and community
Contact through the website.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



