Overlooked on HN: Discovering High-quality Technical Content
I’m gonna start a column on cool blog posts I found, that got 0 or minimal traction. I suspect I will also have no traction doing that 🤦♂️.
I really enjoy thoughtful writing on deep technical problems. It’s even better when one sees thoughtful comments, that further contribute new directions to throughts presented. HackerNews is where most of that writing tends to land. Unfortunately it tends to not do well vs trendy, click-baity, etc content. Twitter is even worse.
First, a blog post on my tooling for reading HN.
HN API + LLMs + Readers To The Rescue!
Fortunatelly HN has an API and creative minds come up with clever hacks to boost signal-to-noise. This combined with GPT to make the biggest improvement in my reading habits: HN Summary
Now instead of mindlessly scrolling ever-worsening twitter feed, I mindlessly scroll through 100s of summaries of HN posts and find the good stuff.
Not super happy about relying on Telegram for this, but it’s available on all my devices, has a fantastic bot API and features a nice web UI. I’m considering switching to discord where the UI is a bit less clean, but it has a lot of the same benefits.
There is a potential alternative to algorithms promoting content based on social dynamics. In this future I could get articles recommended based on (shallow/limited) LLM-article-analysis related to questions/thoughts my blogs posts, my comments.
Once I discover something long and interesting, I throw it over into omnivore to maximize readability.
Comments Are A Problem
Unfortunately, I usually find good stuff days or weeks after it was posted (high quality thoughts age well) and most people don’t seem to have reply notifications setup (I use the Telegram hn_replies_bot ), so I rarely get replies to my follow-up questions unless I make the effort to find authors on twitter/discord.