Top all-time · #19425
Marco Maier
Personal blog · marcotm.com/articles · on HN as marcotmaiprogramming
Marco Maier's personal blog at marcotm.com covers ai and programming. Since 2022, 4 different Hacker News readers have linked it 7 times, most often “Information Extraction with Large Language Models”. The last post was in 2024, but the archive is still widely read.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
Commenters link Marco Maier's site for posts on hosting a website from his own C web server and on Hacker News traffic statistics, including the share of visitors from the US. No comment judges the writing.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Marco Maier is a technology entrepreneur. He is CTO at TAWNY and lecturer at the University of Munich.
Most-linked posts?
- Information Extraction with Large Language Models2 people · 4 mentions · first linked 2023-03-22
- /articles/stats-of-being-on-the-hacker-news-front-page/2 people · 2 mentions · first linked 2024-09-25
What Hacker News says?
Even caching is normally unnecessary. Honestly, HN front page traffic isn’t much. For most, it probably peaks at about one page load¹ per second², and if your web server software can’t cope with that, it’s bad . Even if your site uses PHP and MySQL and queries the database to handle every request, hopefully static resources bypass all that and are served straight from disk. CPU and memory usage will be negligible, a…
Comment linking /articles/stats-of-being-on-the-hacker-news-front-page/
on “Show HN: Hosting my website using my C web server”Submitted Information Extraction with Large Language Models as a story · 1 points
HN discussionIndirectly, in a way. A few months ago, I built a small site [1] that parses and structures the "Who is hiring" posts using GPT. It was/is just a personal project to deepen my actual experience in building things with LLMs [2]. After the launch [3], I was actually contacted a few times for LLM-related projects. I am not looking for a full-time job at the moment, but it led to a small consulting/contracting engagemen…
Comment linking /articles/information-extraction-with-large-language-models-parsing-unstructured-data-with-gpt/
on “Ask HN: Who Got Hired?”Submitted Evaluation-Driven Machine Learning as a story · 1 points
HN discussionFair point. I looked it up and I didn't realize that possibly only around 40-50% of HN traffic is from the US https://marcotm.com/articles/stats-of-being-on-the-hacker-ne... I do wonder what similar polling/surveys would find in other countries
Comment linking /articles/stats-of-being-on-the-hacker-news-front-page/
on “Why is the HN crowd so anti-AI?”I wanted to share a little side project of mine that I created while tinkering around with GPT-3. The project uses the Algolia HN Search API [1] to retrieve the "Who is hiring?" posts from HN and then parses them with the help of GPT-3 / GPT-3.5 (I do not have API access to GPT-4, yet, but it already works quite well even with the older models). It then puts the job postings into a structured list that is hopefully…
Comment linking /articles/information-extraction-with-large-language-models-parsing-unstructured-data-with-gpt/
on “Show HN: A structured list of jobs from “Who is hiring?”, parsed with GPT”For many use cases like summarization or information extraction, you can get deterministic and mostly non-creative results by adjusting the parameters (temperature, top-p, etc.). This is only possible via the API, though. And it work's most reliably when providing the whole input which should be worked on ("open book" as another commenter called it). I run a task like this for Hacker Jobs [1] and am quite happy with…
Comment linking /articles/information-extraction-with-large-language-models-parsing-unstructured-data-with-gpt/
on “Building LLM Applications for Production”