Post by Glyph
@nick I absolutely agree that this is painfully difficult to study. It's actually *resistant* to study, because the frontier labs are constantly cooking up benchmarks that they later find are regurgi…
By Glyph
@nick I absolutely agree that this is painfully difficult to study. It's actually *resistant* to study, because the frontier labs are constantly cooking up benchmarks that they later find are regurgi…
By Glyph