How are benchmarks used in model development, and where do they fall short?
SnorkelAI highlights a Frontier Data Summit discussion featuring participants from Laude Institute, Open Athena and Stanford CRFM.
TLDR
SnorkelAI is promoting a Frontier Data Summit discussion about benchmarks’ role in model development and their limitations. It pairs a participant from Laude Institute with an Open Athena technical staff member who also leads research engineering at Stanford CRFM.
Combined views
1
1 Source, first seen ago
4 reposts
