Pretty cool! It reminded me of this work from NVIDIA Research - https://nvidia-ai-iot.github.io/remembr where they used VLMs and RAG on top of a real robot to navigate the Voyager campus in Santa Clara. You also might like the new OpenAI o3 models and how well they can play GeoGuessr ;)

https://simonwillison.net/2025/Apr/26/o3-photo-locations, https://news.ycombinator.com/item?id=43835044, https://www.astralcodexten.com/p/testing-ais-geoguessr-geniu...

Yep I've seen the NVidia research stuff. It's pretty cool.

Congrats on the launch! I'm one of the authors of that paper you cited, glad it was useful and inspiring to building this :) Let me know if we can support in any way!

Wow! I enjoyed reading it a lot and it was definitely inspiring for this project!

Would love to talk to you about it and make sure we capture all of the pain points if you're open to it? :)

Absolutely, will DM you on X!

It provides the easiest and fastest way for developers to build retrieval-augmented generation (RAG) chatbots, without needing any local GPU setup. Code is on NVIDIA's GitHub and is ~100 lines of Python.

I wanted to share a blog post I wrote, about transitioning teams in NVIDIA from working on self-driving, to working on generative AI and large language models (LLMs). I intend to post more frequently about applications of LLMs/GenAI in various domains, based on the work I am doing. Feedback on this post and suggestions on what I could write about are greatly appreciated!