Top all-time · #15782
Data Science Castnet
Personal blog · datasciencecastnet.home.blogdataprogramming
Data Science Castnet is a personal blog at datasciencecastnet.home.blog about data and programming. Since 2021, 5 different Hacker News readers have linked it 7 times, most often “DistilHN: Summarizing News Articles with Transformers”. The last post was in 2023, but the archive is still widely read.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
Data science blog covering reinforcement learning for game agents, a write-up of the Distilhn front-page summarizer, and generative music. HN commenters link its posts as project write-ups.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Playing with data, writing tutorials and sharing my findings as I trawl through the world of data science
Most-linked posts?
- DistilHN: Summarizing News Articles with Transformers3 people · 3 mentions · first linked 2022-12-30
What Hacker News says?
Letting these ML agents loose on your game is also a good way to discover bugs in the implementation that a human player might never run into. When I first messed about with RL[1] I quickly discovered this, with my 'AI' learning to abuse invalid moves to get a re-roll of the dice or to stay put when it should have been forced to move. [1] - https://datasciencecastnet.home.blog/2020/01/24/swoggle-part...
Comment linking /2020/01/24/swoggle-part-2-building-a-policy-network-with-pytorch-dealing-with-cheaty-agents-and-beating-the-game/
on “Learning Machine Learning for Game Development”Submitted DistilHN: Summarizing News Articles with Transformers as a story · 2 points
HN discussionSome sounds OK, most sounds like a series of plausible notes that nevertheless don't actually go anywhere. Most generative models tend to do OK at predicting the immediate next note, say, but they can't keep a macro-level structure unless you force that as a constraint. For me what has worked best is generating music and then re-interpreting that with some manual post-processing to get it into a less jarring form. A…
Comment linking /2021/05/13/whistlegen-generating-traditional-irish-music-with-ml/
on “Show HN: AI-Generated Illustrations of Plants”Submitted Exploring Softmax1, or “Community Research for the Win ” – Data Science Castnet as a story · 1 points
HN discussion1. It depends, if you just want to use some model and call APIs, then you do not have to learn any ML theory. You just have to learn using libraries following their GitHub Readme instructions. Get a Colab Pro+ subscription or run Kaggle Notebooks for free. You can also simply use GUIs built on top of Open Source models. 2. Learn to use the Hugging Face library, and use their stuff on your Notebooks. 3. Learn some ML…
Comment linking /
on “Ask HN: How to get into AI generation(images,text)”Any chance you'll open source all this? It could serve as a nice foundational layer / harness / framework for many purposes. Edit: I found your explanatory post ( https://datasciencecastnet.home.blog/2022/12/30/distilhn-sum... ), not yet totally clear whether it includes enough information to be considered an end to end tutorial, but it's certainly a generous start. Thank you!
Comment linking /2022/12/30/distilhn-summarizing-news-articles-with-transformers/
on “Show HN: Distilhn.com – Front-Page Articles Summarized with Machine Learning”This was a fun little Christmas project. I did a quick write-up and video here: https://datasciencecastnet.home.blog/2022/12/30/distilhn-sum...
Comment linking /2022/12/30/distilhn-summarizing-news-articles-with-transformers/
on “Show HN: Distilhn.com – Front-Page Articles Summarized with Machine Learning”