The project is in an experimental, pre-alpha, exploratory phase with the intention to be productionized. We move fast, break things, and explore various aspects of the seamless developer experience ...

Your browser has hidden superpowers and you can use them to automate boring work.

I tried four vibe-coding tools, including Cursor and Replit, with no coding background. Here's what worked (and what didn't).

Please cite this work with the following BibTeX: @inproceedings{cocchi2024augmenting, title={{Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering}}, ...