AI Engineering the Acceleration Whiplash

#1

Post by DareTheDev » Fri, Jun 12, 2026, 8:36 AM UTC

AI Engineering the Acceleration Whiplash
faros.ai

Re: AI Engineering the Acceleration Whiplash

#2

Post by fnl » Fri, Jun 12, 2026, 12:06 PM UTC

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.

Re: AI Engineering the Acceleration Whiplash

#3

Post by pier25 » Fri, Jun 12, 2026, 3:13 PM UTC

fnl wrote: post #2

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".

Re: AI Engineering the Acceleration Whiplash

#4

Post by fnl » Fri, Jun 12, 2026, 7:10 PM UTC

fnl wrote: post #2

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.

Update: on LinkedIn the Faros team replied to me and stated that they see both usage and issues increasing over time.

Re: AI Engineering the Acceleration Whiplash

#5

Post by DareTheDev » Fri, Jun 12, 2026, 7:22 PM UTC

fnl wrote: post #4

fnl wrote: post #2

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.

Update: on LinkedIn the Faros team replied to me and stated that they see both usage and issues increasing over time.

Nice