MediaScout Weekly

Sign in Subscribe

Latest

LLM Citations Are Guesses. Source Tracking Makes Them Receipts

LLM Citations Are Guesses. Source Tracking Makes Them Receipts

C²-Cite raised citation quality by an average of 5.8% and response correctness by 17.4% on the ALCE benchmark. And the gap between those two numbers is the story. LLM citation and source tracking is the discipline of proving that every claim in a model's output

Procedural Graph Architectures Are Rewiring Self-Evolving Agents

Procedural Graph Architectures Are Rewiring Self-Evolving Agents

Open-Source LLM Toolchains Now Run Entirely Local

Open-Source LLM Toolchains Now Run Entirely Local

Open-Source Multimodal LLMs Now Take Audio and Video Natively

Open-Source Multimodal LLMs Now Take Audio and Video Natively

Open Source Long Context LLMs Went 1M. Demand Proof.

Open Source Long Context LLMs Went 1M. Demand Proof.

WearableQA Tested 14 Models. Most Fell Below 60%.

WearableQA Tested 14 Models. Most Fell Below 60%.

Open-Source Multi-Agent Frameworks: The Ones I'd Actually Ship

Open-Source Multi-Agent Frameworks: The Ones I'd Actually Ship