Honestly, this looks like the only LLM summary use case that sounds remotely useful for me. My only gripe, after looking for the cached example, is how verbose it is.
I would prefer just a one-sentence summary of what it is and one-line header explanations for comment topics to point me to the right place in the discussion.
In general, in my opinion, this is more useful as a navigation aid to help me quickly judge whether the discussion is interesting than as a replacement for the original text. But it could be way too out of scope for this tool. (I wish something like that existed for scientific peer-review journals...).
Thanks for the feedback. The system prompt for the web app is optimized to balance between too short a summary vs not long enough. The browser extension, on the other hand, allows you to customize the system prompt to make the result exactly the way you want.
Another option is to look at the Bluesky feed [0]. This bot looks at top stories in HN and creates a very short summary. It only does around 20 posts a day. That could be limiting too.
I would prefer just a one-sentence summary of what it is and one-line header explanations for comment topics to point me to the right place in the discussion.
In general, in my opinion, this is more useful as a navigation aid to help me quickly judge whether the discussion is interesting than as a replacement for the original text. But it could be way too out of scope for this tool. (I wish something like that existed for scientific peer-review journals...).