-
Without these, Claude will be confidently wrong.
8 min read -
Enterprise Document Intelligence [Vol.1 #5quater] – The other parsers read the words on a page.…
15 min read -
A systems-level deep dive into the hidden microarchitectural costs of Kubernetes GPU time-slicing, and what…
22 min read -
Increasing context size in RAG systems doesn’t improve accuracy for aggregation tasks—it makes errors harder…
15 min read -
Enterprise Document Intelligence [Vol.1 #5ter] – Table cells, OCR, captions, headings: cloud-grade structure, running on…
19 min read -
Let’s practice data science thinking through a probability problem
9 min read -
Enterprise Document Intelligence [Vol.1 #5bis] – The same relational tables. Native table cells. OCR for…
16 min read -
Why Decade-Old Residual Connections Still Power All of AI (And Why That’s a Problem)
Large Language ModelsFor nearly a decade, this part of neural networks barely changed. DeepSeek is trying to…
16 min read -
Claude can now write its own harness on the fly, custom-built for the task at…
28 min read -
I tried to make my ETL pipeline production-ready. Three things broke. Each one taught me…
9 min read
