Hacker Newsnew | past | comments | ask | show | jobs | submit | samixg's commentslogin

https://mythos.so/

an AI-native book reader that actually understands what you’re reading.

You highlight text, and the app infers intent and surfaces the right actions inline.

Examples:

Highlight a confusing paragraph → auto-suggests questions like “what does this term mean?” or “how does this relate to earlier chapters?”

Highlight a name → instant character context (no spoilers)

Highlight an argument → concise breakdown, assumptions, counterpoints

It works across EPUBs, PDFs, and papers, and the core rule is: AI should be assistive, never intrusive. No prompts required, no context switching.

Built it because I read a lot of dense material and hated breaking flow.


Are you planning to release it for Android?


Yes I do, there's a plan for an Android/Web version


it took me a while to understand how to play it, but holy shit this is impressive! nice work


similar in the sense that they're both influenced by determinism.

funny enough, i wrote a draft blog post about what it would take "in theory" to be able to predict the future, but never got to finish it.


interesting, this reframes the question to "how long would it take until something significant goes out of sync", in that case i do agree with you, there'll be some mysterious period of time the two universes staying in sync, potentially infinity


A Vision For An Education System Built Around Curiosity, Mentorship, And Real-world Learning. Without Schools, Grades, or Fixed Paths.


usually you don't, but writing mini-essays helped me with complex topics


Let me know if you have any feedback!


Fair point, I did try to include the job requirements in the before/after but couldn't integrate it in a pleasant way, but if you're interested here's the job post I used for the example: https://apply.workable.com/lucidya/j/47F7F41A30/


This is so cool!

I think Resume.Ink is different because it generates a new PDF resume tailored specifically to the job you're applying to. While JSON Resume generates a cover letter. I think they actually complement each other quite well.


Yeah my bad, I just tried to delete my comment but too late.

---

My useful feedback;

  - I thought the UX was broken when there was no next button after answering questions

  - It would be great if the homepage showed a real example (real JD, real before and after) 

  - There was a bug in my upload (Thomas Davis pdf if you are looking at the database). It hallucinated a whole job I've never had into my finished resume.


Don't worry, I'm pretty sure someone will find your comment useful

--------

Thanks for the feedback: 1. You're right, the UX can use some improvements there 2. I've just updated the landing page with a before/after example 3. Ooh, that's not good, thanks for reporting this, I'll look into it asap


I'm also working on a similar feature, it's simple but complicated too "merge" information in when using GPT's. I imagine you've encountered it too. If I say I have an array of interests ['music', 'gardening', 'racing'], and a GPT replies ['music', 'gardening', 'racing', 'competitive driving'], you don't want additive synonyms. And then more complicated is deletions, if it replies, ['gardening', 'racing', 'skydiving'], does that mean I want to remove 'music' or did it just forget to include it in the response so should I just merge the old and new array.

I'm probably going to open source a llm-structured-data-merge-thingy library (that has different merge strategies) in the near future.


Yeah, it's pretty complicated. I didn't really solve it, but I'd be interested to see how you do it.


That's a great suggestion, I'll add a FAQ section to answer these.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: