News for hackers. Stuff that matters.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by reversengineer on Tuesday November 17, 2026 @04:51PM (#50538736)
Is it me, or do the results seem to show a lack of significant difference between both models? And, because of the potential non-determinism in Generative AI to create a huge degree of variance in outcomes, I am dubious about the repeatability of these results.
Re:In 27,280 coding agent runs, 64% of inference spend went ... by Edward40 on Tuesday November 17, 2026 @05:07PM (#50538927)
We ran 4 attempts per task, that's just like when you roll dice 4 times.