Hacker News Reader

Comment by slopdo | Hacker News Reader

Is there any mechanism to prevent the AI from answering with spoilers? For example, when I ask about a character I don't want information coming from pages/chapters I still didn't read.

View on HN

Thank you for the sharp feedback.

Because we've been mainly targeting business and technical books, the spoiler-prevention feature is not yet implemented.

However, to make novels and other narratives comfortable to read in the future, I'll definitely consider adding a feature to limit the AI's knowledge based on your reading progress.

Thanks again for the valuable suggestion!

Claude, is that you?

Since my native language is not English, I use LLM as a translation tool. I am sorry if I have made you feel that the text is inorganic.

Just answer to the best of your ability in English, or if you can't do that then write in your own language and translate that text. The responses currently look like you're asking AI to completely come up with the responses for you rather than including any of your own thoughts.

I guess it’s better for non-fiction books in that case. Similarly I would be upset if the LLM spoiled a fiction book somehow.. like figuring out which characters will die in GoT before reading it.

I also assumed this is for non-fiction books but then I checked the Github page and the first video shows Alice in Wonderland as an example. This is the reason I asked.

Yup, think it's just a poorly chosen example. Although Alice in Wonderland does relate to Mathematics, so maybe it's a better chosen example than we realize!

This is a crucial feature - perhaps implementing a "reading progress tracker" that masks content beyond your current position would make this truly useful for fiction.

Reply on news.ycombinator.com