Gray Swan AI
Stanford University
Neil ChowdhuryMember of Technical Staff · Thinking Machines LabResearcher↗
Researcher
Eliot Krzysztof Jones
Thinking Machines LabMember of Technical Staff
Career & education
Current roleThinking Machines LabSep 2026-presentMember of Technical Staff
Thinking Machines LabSep 2026-presentPreviously
HarkFeb 2026-Aug 2026Member of Technical Staff
HarkFeb 2026-Aug 2026Head of Offensive SecuritySep 2025-Jan 2026
AI Safety and Security Research EngineerOct 2024-Sep 2025
Education
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
References
- A New Framework for Cybersecurity Refusals in AI Agentsarxiv.org
Jones is first author on a framework for testing whether cybersecurity agents refuse harmful requests.
- Stanford CRFM — Cybenchcrfm.stanford.edu
Lists Jones as co-author and explains the benchmark tasks from cybersecurity competitions.
- Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testingarxiv.org
Lists Jones as co-author and describes the live university network study.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
