@communist@lemmy.frozeninferno.xyz
Post #1302711
2026-03-28 22:01 UTC
They get 85% on the last benchmark, this one was specifically designed to stump them, when the last one came out everyone said the same things as this go around.
will anyone be retracting their statements when they get to 85% on this one?
Replies (1)
-
@Noja@sopuli.xyz 2026-03-28 22:33
So they already have AGI? Why doesn't it solve new problems then? Bunch of bullshit, they're just adjusting their models to the "benchmarks" to get more VC funding