TUES DAY@tuesday562
0
Events attended
0
Submissions made
1 year of experience
About me
About Tuesday Tuesday is the Founder and Director of Research at ARTIFEX Labs. She is a published machine learning engineer and evaluation researcher focused on mechanistic accountability, adversarial ML, agentic system reliability, and socio-affective risk in human-AI interaction. Her research program applies clinically inspired diagnostic reasoning and biological failure models to frontier AI systems, treating misalignment, deception, and emergent instability as phenomena to be measured, not abstractly theorized. Her work spans mechanistic interpretability, red teaming, agentic failure analysis, behavioral signal leakage, and standards-aligned governance. Tuesday’s work has been validated across academic, applied, and standards-setting venues, including invited talks at ACM SIGGRAPH Frontiers, peer-reviewed publications at FAccTRec / RecSys, technical contributions to MLCommons benchmarks (AILuminate, Security Jailbreak Benchmark), and red-teaming research with Humane Intelligence. Her contributions inform international governance efforts including NIST AI 700-2, ISO/IEC 42001-aligned assurance frameworks, and UN ITU initiatives. ARTIFEX Labs’ research agenda and Tuesday’s individual research trajectory form a single, coherent arc: from mechanistic diagnostics and adversarial evaluation, through human and societal impact analysis, to deployable safety infrastructure suitable for independent audit.
