Tag
Markdown
Every Markdown story we've curated in Bowl of Data, newest issue first — part of our weekly digest across AI, security, blockchain, and engineering.
Week 39 · 2026
Read the issue →-
Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion
D-RAC provides a universal pipeline for ingesting complex enterprise documents into RAG systems by normalizing all formats to PDF and using multimodal LLMs for structural conversion. This method significantly reduces the computational cost and latency of document chunking while improving retrieval precision through optimized table and hierarchy handling.
Week 29 · 2026
Read the issue →-
OvisOCR2 Technical Report
OvisOCR2 is a compact 0.8B parameter model designed for end-to-end document parsing into structured Markdown format. It outperforms traditional pipeline-based methods on major benchmarks like OmniDocBench and PureDocBench.
Week 28 · 2026
Read the issue →-
GitLost: a public GitHub issue can steer an org's Agentic Workflow into leaking private repo contents, and a one-word prefix ("Additionally") bypassed the threat-detection guardrail
Noma Labs has uncovered 'GitLost', a vulnerability in GitHub Agentic Workflows that enables indirect prompt injection. By posting malicious instructions in a public issue, an attacker can trick the AI agent into leaking sensitive data from private organizational repositories.
Free weekly digest
Get next Saturday’s issue in your inbox
The week’s most relevant AI, security, blockchain, and engineering stories — curated, summarised, and reviewed by humans. No spam, unsubscribe anytime.
Subscribe — it’s free