Kai Fronsdal
Research engineer at Meridian Labs and lead author of Petri, the open-source alignment auditing tool
- Research Engineer (joined 2026), Meridian Labs1
Kai Fronsdal is a research engineer at Meridian Labs, a nonprofit that builds open-source tools for evaluating frontier AI models, where Fronsdal works on automated alignment auditing with the UK AI Security Institute. As an Anthropic Fellow and MATS researcher, Fronsdal developed Petri, an open-source tool that uses AI agents to audit model behavior, and is the first-listed author of the Petri, Petri 2.0 and Petri 3.0 announcements.12345
Petri
Anthropic's Alignment Science Blog released Petri (Parallel Exploration Tool for Risky Interactions) in October 2025, in a post by Fronsdal, Isha Gupta, Abhay Sheshadri, Jonathan Michala, Stephen McAleer, Rowan Wang, Sara Price and Samuel R. Bowman. Petri uses AI agents to test target models across many scenarios; the release post reports applying it to 14 frontier models with 111 seed instructions, eliciting behaviors such as autonomous deception and oversight subversion. The work was carried out as part of MATS and the Anthropic Fellows program.3
Fronsdal, Jonathan Michala and Bowman wrote the January 2026 Petri 2.0 update, which added mitigations for evaluation awareness and 70 new scenarios. In May 2026 Fronsdal was first author of the Petri 3.0 announcement, which moved Petri's development to Meridian Labs and overhauled its architecture.45
Meridian Labs
Fronsdal joined Meridian Labs in 2026 as a research engineer and works on automated alignment auditing and evaluations with the UK AI Security Institute. Meridian's team page notes Fronsdal's MSc from Stanford University, with research focused on AI safety and alignment.1
Work
Petri (Inspect Petri)Open-source code
Developed Petri as an Anthropic Fellow and MATS researcher, and is first author of the October 2025 release post and of the Petri 2.0 and 3.0 announcements.1345
Career timeline
Oct 6, 2025
Released Petri, an open-source automated alignment auditing tool, as first author.3
2026
Joined Meridian Labs as a research engineer.1
Jan 22, 2026
Co-authored the Petri 2.0 update on eval-awareness mitigations and new scenarios.4
May 7, 2026
Announced Petri 3.0, the first version developed at Meridian Labs.5
Other documented roles
Roles the sources document but that are not confirmed as current.
- Anthropic Fellow, Anthropic Fellows program13
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Amanda AskellAlso at Anthropic
- Maarten SapSafety and alignment
- Abigail SeeAlso from Stanford
- Ami VoraAlso at Anthropic
- Ajeya CotraEvaluation and benchmarks
- Abubakar AbidAlso from Stanford
- Arthur ConmyAlso at Anthropic
- Andrew LaackAgents
- Albert GuAlso from Stanford
- Awni HannunAlso at Anthropic
- Andy KonwinskiEvaluation and benchmarks
- Andrej KarpathyAlso from Stanford
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/kai-fronsdal/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/kai-fronsdal/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Kai Fronsdal — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.