AI Engineering the Acceleration Whiplash
faros.ai
1 thread
2y of data. They should address that confounder and demonstrate the results are stable even if you stratify over time. 2026 models are very different from 2024 ones, after all.
I'm not saying there haven't been improvements but personally I would not classify those as "very different".
Update: on LinkedIn the Faros team replied to me and stated that they see both usage and issues increasing over time.
Nice