News for hackers. Stuff that matters.

A comment on Claude Fable 5.2 and Mythos 5.2.

Re:Claude Fable 5.2 and Mythos 5.2 by iamdelirium on Monday November 09, 2026 @02:09PM (#50430137)
FrontierCode 2.0 is such a poor benchmark for Gemini since it's the only model forced to not use its own harness but Devin CLI.

I wonder why that team singles Gemini out like that.

[ Parent | on HN ]
Re:Claude Fable 5.2 and Mythos 5.2 by mattlondon on Monday November 09, 2026 @02:38PM (#50430704)
Probably can't work out how to sign up for the API!
[ Parent | on HN ]