I like the idea, but this is going be a very very long journey to develop a completely new machine-friendly language like this while LLMs still have many limitations now.
I built a website (https://hpyhn.xyz) for hacker news users for reasons:
1. hn comments are valuable, I've spent a lot of time going through hn comments. I think there are valuable comments buried in the threads with fewer points, so it's not enough to just read top3 threads.
2. Sometimes a good post is ignored due to a bad title, sometimes I still have no idea what the post's theme even after I read a few paragraphs.
3. I want to filter out some posts I'm not interested in, but I realized I need read some other posts it's not a simple yes/no problem, so I gave every post a interesting score based on my own preference
so I built this tool to save my time while not missing out too much on hn
I built a website (https://hpyhn.xyz) for hacker news users for reasons:
1. hn comments are valuable, I've spent a lot of time going through hn comments.
I think there are valuable comments buried in the threads with fewer points, so it's not enough to just read top3 threads.
2. Sometimes a good post is ignored due to a bad title, sometimes I still have no idea what the post's theme even after I read a few paragraphs.
3. I want to filter out some posts I'm not interested in, but I realized I need read some other posts it's not a simple yes/no problem, so I gave every post a interesting score based on my own preference
so I want a tool to save my time while not missing out too much on hn
> Brittle performance – A model might do well on short, primary school-style maths questions, but if you change the numbers or wording slightly, it suddenly fails. This shows it may be memorising patterns rather than truly understanding the problem
As an indie hacker I often struggle to find new ideas. Are there any practical strategies for discovering these real pain points?