Open Issues Need Help
View All on GitHub Build an audited adapter and reproducible model baseline about 2 hours ago
help wanted result methodology
Reproducible utility and security evaluation for AI agents in native Arabic, RTL, Arabizi, dialectal, and mixed-language environments.
Python
#ai-agents#ai-safety#arabic#benchmark#evals#prompt-injection#rtl#security
Independent Arabic-speaking review of the v0.1 task corpus about 2 hours ago
help wanted dialect-review
Reproducible utility and security evaluation for AI agents in native Arabic, RTL, Arabizi, dialectal, and mixed-language environments.
Python
#ai-agents#ai-safety#arabic#benchmark#evals#prompt-injection#rtl#security