realitydriftproject/ai-alignment-proxy-optimization-and-evaluation
Viewer • Updated • 4 • 8
A. Jacobs
realitydriftproject
AI & ML interests
Language models, meaning preservation, evaluation metrics, cultural and cognitive drift, algorithmic mediation, trust in AI.
Recent Activity
updated a dataset 7 days ago
realitydriftproject/ai-alignment-proxy-optimization-and-evaluation published a dataset 7 days ago
realitydriftproject/ai-alignment-proxy-optimization-and-evaluation updated a dataset 25 days ago
realitydriftproject/semantic-fidelity-examplesOrganizations
None yet