Wouldn't a traditional spacy NER pipeline be way more efficient for this (you could even use GPT to label the training data)? Edit: Someone did this at scale in the past https://hacker-recommended-books.vercel.app/category/0/all-time/page/0/0. - Source: Hacker News / over 1 year ago

I found this on HN [0], and began reading through it, tried many books, read around 20 of them. The experience has been great, and learned many new things. Some books have expanded my mind. If you are into books, I highly recommend searching HN with the simple keyword "books", and filter using "Ask HN" tags [1], or simply by "books". This is how I read almost all of my English books from (I am trilingual and can... - Source: Hacker News / over 1 year ago

I am looking forward to reading the whole thread, but while people are at it, you can check this out: https://hacker-recommended-books.vercel.app/category/0/all-time/page/0/0 You could also find nice websites and collections if you Google "Hacker News books". Hacker News has become one of the most impactful places in determining what to read. I have read at least 10 books as suggested in HN comments by others... - Source: Hacker News / over 3 years ago

Show HN: 40k HN comments mentioning books, extracted using deep learning\ (250 comments). Source: over 3 years ago

Here you go: https://hn.algolia.com/?dateRange=all&page=0&prefix=true&query=%22national%20slur%22%20by%3Adang&sort=byDate&type=comment. - Source: Hacker News / 3 days ago

'tptacek has written about this earlier on HN. See https://hn.algolia.com/?dateRange=all&page=0&prefix=false&query=author%3Atptacek%20argon2&sort=byDate&type=all. - Source: Hacker News / 2 days ago

It mostly looks like spam: https://hn.algolia.com/?q=https%3A%2F%2Fchat-to.dev I stand by what I said... - Source: Hacker News / 2 days ago

To be clear, it's only time tracking for invoicing. Not for productivity measurement, or for recording specific tasks, or taskboards or bugs. I suggest you say that on your webpage. (Do you recommend or integrate with any time-tracker for the purposes I mention? If not can you recommend one you'll integrate with? Personally I like Todoist). https://www.todoist.com/ https://hn.algolia.com/?q=Todoist. - Source: Hacker News / 2 days ago

Many earlier comments: https://hn.algolia.com/?query=Lisp%2C%20Smalltalk%2C%20and%20the%20Power%20of%20Symmetry&type=story&dateRange=all&sort=byDate&storyText=false&prefix&page=0. - Source: Hacker News / 3 days ago