documents

documents at Beyond Market Intelligence is a file of 5 stories. The newest of them: “Four AI Retrieval Methods Benchmarked for Real-World Trade-offs”, “DOJ second request puts Fox's Roku acquisition under deeper scrutiny”, and “Build the Index Before You Open the Folder”. Four retrieval architectures, one laptop, and a single set of documents. Fox's $22 billion bid for Roku just met the Department of Justice's most deliberate question yet. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every documents story on Beyond Market Intelligence, newest first.

Four AI Retrieval Methods Benchmarked for Real-World Trade-offs
Towards Data Science

Four AI Retrieval Methods Benchmarked for Real-World Trade-offs

Four retrieval architectures, one laptop, and a single set of documents. That's the setup for this hands-on experiment, which benchmarks plain RAG, graph RAG, and a frontier model's context window against the same questions. The results offer a practical look at when graph RAG earns its complexity. For those exploring how AI structures understanding, our related piece on verifying AI comprehension in tax season is a natural next step. The trade-offs here are worth your attention.

DOJ second request puts Fox's Roku acquisition under deeper scrutiny
TechCrunch

DOJ second request puts Fox's Roku acquisition under deeper scrutiny

Fox's $22 billion bid for Roku just met the Department of Justice's most deliberate question yet. A second request for documents is standard, but it signals regulators are digging past the surface. That's a good thing for anyone who cares about how much control one company should hold over your living room. This deal isn't just about streaming; it's about data.

Build the Index Before You Open the Folder
Towards Data Science

Build the Index Before You Open the Folder

A case file is more than a stack of PDFs, and the index proves it by mapping what the case type demands before a single folder is opened. The two questions worth building for are not retrieval questions at all, which reframes how we think about RAG's purpose. It's a sharp, practical push toward relational tables that serve the work. For deeper context on how LLMs handle structure, our related piece on paragraph structure and token space pairs well here.

Waymo's collision probe documents remain hidden behind confidentiality claims.
TechCrunch

Waymo's collision probe documents remain hidden behind confidentiality claims.

Waymo has handed over documents in NHTSA's child collision probe, but the responses so far arrive heavily redacted, with the company citing "confidential business information." That is a curious stance for a firm asking the public to trust its judgment on the road. Transparency matters most when scrutiny intensifies, and blacking out entire answers invites more questions than it settles. For deeper context on how data exposure and trust intersect, our piece "Protecting Data in the Age of AI-Powered Apps" offers a useful lens.

Explore how a native JSON API simplifies data handling in JDK 28.
InfoQ

Explore how a native JSON API simplifies data handling in JDK 28.

JEP 540 has moved to Target status for JDK 28, and that's worth paying attention to. It brings a compact JSON API that handles parsing and generating documents without dragging in external dependencies. The immutable value hierarchy keeps things clean, and strict syntax rules mean fewer surprises. What stands out is the focus on core tasks, not endless features. Feedback during incubation will refine it further. For developers tired of bolting on libraries for basic JSON work, this feels like a step toward simpler workflows.