Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.
If you arrived here through a search or shared link, this page collects the links I found for RAG for the week ending August 14, 2026.
As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.
This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.
Category Cover Image Prompt: A single cream index card lying flat and centered on a vast expanse of still pale water meeting a misty indigo dawn horizon, one corner gently lifted and catching a thin thread of warm gold light, photorealistic magazine cover minimalism with vast negative space, the bold word RAG set large and clean in the open sky above.
This Week in RAG News
Summary by Claude Sonnet 5.5 based on this week’s links:
Scott Stevenson argued that RAG and harness engineering still beat training a custom model most of the time. His reasons: they can personalize per customer, avoid leaking private data, and work in real time.
Separately, Cohere released North Micro Vision, its smallest vision-language model, under Apache 2.0 with weights on Hugging Face. Cohere says it is aimed at document understanding and beats Gemma 4 E2B and Ministral 3 3B on visual benchmarks.
This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.
This week's links related to RAG
Have warned about the cognitive bias that makes training seem appealing since 2022:
https://t.co/lnDicsNKHk But RAG and harness engineering still win most of the time: 1) It can personalize a system per customer 2) It doesn’t risk spitting out private data 3) Its realtime 4)”
https://x.com/scottastevenson/status/2087511232169308371
The model punches above its weight, outperforming Gemma 4 E2B and Ministral 3 3B across a broad range of visual understanding benchmarks and delivers particularly strong results on document understanding and visual Q&A. See the full results:
https://x.com/cohere/status/2087571579517489581
this week in open source: – Muse-Glimmer-30B – LTX 2.5 – Nemotron 3.5-Lightning – Ling3.0-tiny – Qwen3.8-2.4T – LFM2.5-VL-3B – Wan2.2-Animate-2 – Cohere North-Micro-Vision and there’s more coming 🤭”
https://x.com/multimodalart/status/2087576052457513234
Today, we’re adding another member to our model family. Meet North Micro Vision. Our smallest vision-language model yet, ideal for sophisticated document understanding. Available open-source under an Apache 2.0 license. Get the weights on @huggingface.”
https://x.com/cohere/status/2087571573947392419
Leave a Reply