Edward Paul

In my first update post I turned down a suggestion. Someone with nineteen years in banking software asked for control totals, checking that the numbers on a document add up, and I said no. Getting there meant giving fields types, then converting formats, then summing, then comparing, and I thought all four of those belonged to a layer above this one. I have now built the first two, and I want to explain what moved.

What moved was not the argument. It was hearing the same thing from people who had never read that thread.

I'm curious: how do you evaluate and compare proxy providers?

Inside the ScrapeOps Proxy Aggregator, we've integrated around 50 proxy providers into a single tool. We continuously test and benchmark them to determine which providers offer the best performance at the lowest cost for different target websites.

The main performance metric we've settled on is average success latency:

How quickly does a provider return a successful response?

The models got dramatically smarter this year. Your product didn't get more trustworthy and in 2026, those turned out to be two completely different problems.

Here's the line that reframed it for me. Stanford's AI Index this year leans on a phrase from Ethan Mollick the "jagged frontier" to describe how these systems excel and then fall off a cliff with no warning. Their example is almost too good: an AI model can win a gold medal at the International Math Olympiad and still not reliably tell time from a clock face. Genius and incompetence living in the same box, and no obvious seam between them.