raunakchowdhuri

The big one is that LLMs get lazy on repetitive tasks. They'll skip rows or consolidate entries instead of grinding through every last one. So you need verify-and-re-extract loops rather than single-pass processing. Breaking work into sub-agent chunks with explicit correctness criteria defined upfront (e.g., "line items must sum to the stated total") lets the system self-verify autonomously. At scale (28M+ fields), this approach actually outperformed expert human labelers!

We've made a lot of changes in the past few months that make our standard extract much, much better, as well as Deep Extract for documents even longer than that. We'd love for you to give it a try!

Have a slack channel with them, these are the versions they mentioned: posthog-node 4.18.1 posthog-js 1.297.3 posthog-react-native 4.11.1 posthog-docusaurus 2.0.6

We're fixing it! This for some reason happens on only _some_ phones in our office so was hard to repro. I think has to do with Safari rendering. Will tone down our WebGPU usage

dang no way! we were both in boston too

this is exactly where we're going with this! glad you see the vision :)

yep!

comparisons to more outputs coming soon!