Roxy

Shieldzzz

1

AI & ML interests

None yet

Recent Activity

new activity 12 days ago

lmsys/mt_bench_human_judgments:Measured: GPT-4 agrees with humans 88% of the time here and still overstates its own win rate by 12.7 points

new activity 12 days ago

lmsys/mt_bench_human_judgments:Measured: GPT-4 agrees with humans 88% of the time here and still overstates its own win rate by 12.7 points

View all activity

Organizations

None yet

New activity in lmsys/mt_bench_human_judgments 12 days ago

Measured: GPT-4 agrees with humans 88% of the time here and still overstates its own win rate by 12.7 points

#4 opened 3 months ago by

Measured: GPT-4 agrees with humans 88% of the time here and still overstates its own win rate by 12.7 points

#4 opened 3 months ago by