Joshua Fonseca

joshycodes

1

·

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

Open-Eval-Commons/OpenEval:Add safety-benchmark responses and judge scores for 7 benchmarks (192 models) -- Item Response Theory for AI Safety, arXiv:2608.05086

published a dataset 8 days ago

metasafetybench/metasafetybench-data

updated a dataset 13 days ago

joshycodes/activation-control-battery

View all activity

Organizations

New activity in Open-Eval-Commons/OpenEval 4 days ago

Add safety-benchmark responses and judge scores for 7 benchmarks (192 models) -- Item Response Theory for AI Safety, arXiv:2608.05086

#3 opened 4 days ago by

Add safety-benchmark responses and judge scores for 7 benchmarks (192 models) -- Item Response Theory for AI Safety, arXiv:2608.05086

#3 opened 4 days ago by