Show HN: Lexiscore – a nutritional label for food for thought
1–10 of 14 posts
Re: Show HN: Lexiscore – a nutritional label for food for thought
#2Hi 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 and all sorts of other nasty failure modes listed in the write-up. Unlike traditional recommendation systems, the lexiscore uses a language model which has access to your written notes. It estimates how surprising different content items are for you based on the model's perplexity in reconstructing the texts. This way, you can quickly tell which articles are likely to be too boring or too challenging and narrow in on the sweet spot of balanced skill and challenge.
Re: Show HN: Lexiscore – a nutritional label for food for thought
#3This is amazing, I can’t wait to try this out. It’s insane how much brain bandwidth is required to optimize the internet for a positive impact rather that whatever the heck we have now.
Re: Show HN: Lexiscore – a nutritional label for food for thought
#4This is amazing, I can’t wait to try this out. It’s insane how much brain bandwidth is required to optimize the internet for a positive impact rather that whatever the heck we have now.
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.
Re: Show HN: Lexiscore – a nutritional label for food for thought
#5Hi 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 and all sorts of other nasty failure modes listed in the write-up. Unlike traditional recommendation systems, the lexiscore uses a language model which has access to your written notes. It estimates how surprising different content items are…
Hi, I just dabbled with conceptarium. It looks really neat! Thanks for making this!
(Also, you sir, have gained a new blog reader!)
Re: Show HN: Lexiscore – a nutritional label for food for thought
#6This seems a really great idea!
How hard would be to make this into a browser extension?
Re: Show HN: Lexiscore – a nutritional label for food for thought
#7This looks really interesting but the landing page is dense. Tough to determine what this actually does (quickly). I wonder if there is an opportunity to offer a condensed introduction ahead of all the detail? The README is a little better but still not totally clear.
Side note — the first link in the README 404s on GitHub.
Re: Show HN: Lexiscore – a nutritional label for food for thought
#8This seems a really great idea! How hard would be to make this into a browser extension?
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 browser today would essentially mean implementing non-trivial parts of HuggingFace's transformers in Javascript + tensorflow.js or trying to compile PyTorch to WASM or something. Not the most enjoyable tasks, eh..
Re: Show HN: Lexiscore – a nutritional label for food for thought
#9This looks really interesting but the landing page is dense. Tough to determine what this actually does (quickly). I wonder if there is an opportunity to offer a condensed introduction ahead of all the detail? The README is a little better but still not totally clear. Side note — the first link in the README 404s on GitHub.
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 predictable it is.
Indeed, the page is more of a write-up than a landing page. Also, broken link fixed, thanks!
Re: Show HN: Lexiscore – a nutritional label for food for thought
#10Hi 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 and all sorts of other nasty failure modes listed in the write-up. Unlike traditional recommendation systems, the lexiscore uses a language model which has access to your written notes. It estimates how surprising different content items are…
Hi, I just dabbled with conceptarium. It looks really neat! Thanks for making this! (Also, you sir, have gained a new blog reader!)
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://paulbricman.com/reflections/thinking-in-public