Featured essay · Our approach
Fide’s Approach to Embedded Evaluations
How we turn questions about responsibility into experiments on AI behavior, safeguards and human judgment.
By Fide AI · 10 min read
Read our approach →
Insights
Research explained: what the findings mean, what they leave uncertain, and how they can inform decisions about AI.
Featured essay · Our approach
How we turn questions about responsibility into experiments on AI behavior, safeguards and human judgment.
By Fide AI · 10 min read
Read our approach →
Analysis for a broader audience, with technical claims linked back to the research package.
Analysis
Published
Fide traces an AgentDojo scoring correction through evaluator selection, older benchmark versions and the records excluded by our own audit.
By Fide AI · 9 min read
Essay
Published
Fide AI’s approach to embedded evaluations combines frontier AI engineering, safety-critical systems research and humanistic and social inquiry to study trustworthy AI.
By Fide AI · 10 min read
Visual investigation
Published
Fide AI reconstructs a known 29-report URLQuery sequence and audits seven encoded payloads across 187 selected records, tracing submitted instructions, recorded responses and data movement.
By Fide AI · 10 min read
Analysis
Published
Fide AI checked DSEWiki reports against incident records and tracked 78 follow-ups. Higher scores often coexisted with earlier errors or unsupported claims.
By Fide AI · 12 min read
Essay
Published
What faith communities should expect from AI developers, and how their concerns can shape trustworthy AI research.
By Fide AI · 5 min read
Field note
Published
The original launch note for Fide AI's faith-facing evaluation work, now situated within a broader research agenda for trustworthy AI.
By Fide AI · 6 min read
Newsletter
Get new findings, the evidence behind them, and the questions guiding our next studies.