Scholar
Kai Fronsdal
Google Scholar ID: 3bEe1GkAAAAJ
Masters Student, Stanford University
AI safety
AI alignment
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
65
H-index
3
i10-index
2
Publications
10
Co-authors
0
Contact
Twitter
Open ↗
GitHub
Open ↗
Publications
6 items
Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks
2026
Cited
0
Improving Evaluation Realism with Inference-Time Compute and Deployment Scaffolds
2026
Cited
0
Evaluating whether AI models would sabotage AI safety research
2026
Cited
0
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
2026
Cited
0
Putnam-AXIOM: A Functional and Static Benchmark
2025
Cited
0
Lean-ing on Quality: How High-Quality Data Beats Diverse Multilingual Data in AutoFormalization
2025
Cited
0
