Viewing profile — paubric

If you've experimented with Claude's Artifacts, you know how much of an impact good UX can have on dev workflows. We built an internal tool for managing a model's read-write access…

Almost all of this codebase has been produced by issuing high-level directives against pinned files. Pinboard is a command-line tool for managing file references when working with …

context: interned at UiPath on a team doing ML A lot of unnecessary hype indeed, though you can actually throw in occasional OCR/NER blocks in the workflow you design. Most often i…

Thanks for the interest! What I've been playing with in the project is not really a summarizer, though I think it could work well with a summarization model. This one is simply abo…

What it says on the tin: BERT attention per token gets converted to CSS styling to grab the user's attention. The idea came from thinking about content consumption as perceiving la…

Hi there! The first few paragraphs say it all: I was curious about how we might train a virtual assistant to actually help the user reach conclusions, rather than simply throw in t…

I had similar doubts initially. I went for the name they used in the paper: https://arxiv.org/pdf/2102.05169.pdf . It takes the sentence out of its original context. A "contextuali…

Thanks for the thoughtful reply! If I understood correctly, you argue that the lexiscore might still lead you down a rabbit hole, even if through ever more challenging ideas, rathe…

I'm really glad you like it! It should soon get its biggest update yet, related to sharing features / learning in public. More details at the end of this last article: https://paul…

tldr: You add content in a self-hosted web app (e.g. as RSS, PDF, EPUB...), and it measures how interesting it is by trying to reconstruct it with a GPT-3-like model and seeing how…

It could work if the extension called on a server to do the heavy lifting of reconstructing the text with the language model. I have a feeling that trying to do it all in the brows…

Thanks for the kind words! I totally agree, I feel we'll look back at how we currently find online content in a few years from now and wonder how could we possibly be okay with it.…

Hi all, I started experimenting with this new approach to finding valuable content online after I got frustrated with traditional recommendation systems leading to echo chambers an…

That would be a neat little study for one of those people with a casual Obsidian vault of 80K notes: 1. Randomly pick 2 notes 2. Compute semantic distance and minimum traversal dis…

The conceptarium (currently) uses OpenAI's CLIP model which encodes both texts and images into a semantic space so that related items are close to each other. This means that if yo…

Thanks for the thoughtful bit of commentary! It's true, my disproportionate focus on embeddings and no explicit links might have been just an extreme reaction to the current state …