From 5409dabea859beb205c63cb4c6e35265cd39b400 Mon Sep 17 00:00:00 2001 From: Jakub Urban Date: Wed, 1 Jul 2026 17:03:52 +0200 Subject: [PATCH] Add YouTube video link for Marcela's talk at PyData Prague #35. Co-authored-by: Cursor --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 4d16486..d1707da 100644 --- a/README.md +++ b/README.md @@ -43,7 +43,7 @@ How hard is it to find a security bug? We will explore that question through nan This simplicity has limits. The approach may miss obvious issues, hallucinate risky findings, or produce inconsistent results across runs. That is why validation, triage, benchmarking, and human judgment matter, and why the real challenge is building reliable processes around unreliable primitives. -#### Marcela Brichtová Piptová - Getting reliable text when PDFs lie and OCR fails +#### Marcela Brichtová Piptová - Getting reliable text when PDFs lie and OCR fails ([video](https://youtu.be/GmF2607-Y20)) LLMs need text as an input. So before a model can reason about a document, we have to read the text, a step often treated as the "easy part" or a solved problem. But is it?