Show HN: I'm 17 and made a tool to help students study smarter (lira.study)

Great work, I like your website design! But I don't think you should fool people by writing "Join thousands of students studying with LIRA." unless that really is the case (which I doubt[0]).

I'm building some different, but also in EdTech. What did you use for capturing the video demos?

[0]: I'm skeptical of the claim since the site is brand new, doesn't show up on Google and launched on PH today.

You might reconsider describing the free tier as being for "(soon to be) dropouts". It seems to come across as simultaneously insulting to potential users, and dismissive of your own product. (Is the free tier really that bad?)

I'm skeptical about this product, and while my age might introduce (17 year old as well , though no cool project other than some ai made bogus , just learning / looking at cool stuff) with some bias, I have a lot of criticisms. The project seems like an underwhelming alternative to Anki (which I use), enhanced dim wittedly with AI. More importantly, the marketing approach feels misguided. My primary issue is that Projects should be judged on their intrinsic utility, not on the age of their developer. By highlighting "a 17-year-old made this" on platforms like Hacker News, the marketing seems designed to provoke curiosity about young talent rather than showcase the product's actual value. The title appears clickbaity, seemingly calculated to attract attention by leveraging the novelty of youth rather than the product's genuine capabilities.

TLDR :

The core recommendation is simple: let the product speak for itself. Technical innovations should be evaluated on their technical strengths, solving real problems effectively, not on the details of their creators.

So:

- The first example is a multiple choice question being answered by AI.

- “The hero text below says: “LIRA lets you quickly save notes, summarize, and answer questions on any webpage, undetected.” (emphasis in original)

This sounds more like a cheating engine than a “study tool”.

Some feedback: on mobile the videos are cut off so it’s hard to see what the tool does.

"Study smarter" or just make it easier to cheat... you be the judge of that. Maybe we should just go back to doing tests and exams on paper? What was the benefit of going digital with this again?

[flagged]

This product claims to unlock "smarter" studying. How does it make studying smarter?

I'm assuming this uses some LLM to generate answers. How can you guarantee that they are accurate, as you claim?

I'm skeptical of this product simply because I don't believe studying is hard because we don't have enough tools. It's hard because the process to build knowledge is inherently long. It takes patience and revisiting topics and concepts many times. Even if you had all the best content on the subject you want to learn, this wouldn't make your learning much faster/easier. Because in the end of the day, what builds knowledge is repeated exposure to the subject, from multiple angles.

Having keyboard shortcuts could be useful to eliminate some clicks.

For the plans offered, could make it clearer that the premium ones include everything in the cheaper plan + more. Also, providing more details what is included in 'advanced features' and what 'full access' means.

As far as bugs, ran a scan with TripleChecker (https://triplechecker.com/s/704482/lira.study). There are a few error pages accessible not from the homepage but for example via https://lira.study/sign-in after you click upgrade, including https://lira.study/guide.

Some of the footer links (privacy policy etc.) are not on the homepage.

Seeing products like this is just sad.

On a personal level as someone who loves learning, it's sad to see that some people may only value using knowledge to just get to the next spot in life and not really understanding anything for its own sake.

Additionally this is a product that seems to merely extract value and not really give anything back to the world. In fact it damages it.

Shameful

Well, compliments for your work but allow me a note: products, especially modern ones, have a very little shelf life, AI is actually a different kind of search engine, good for some kind of search but easy to allucinate so... It's a dream of some giants to keep ruling the people because they count to be the sole with enough data and resources to train models and probably use training biases to direct popular opinion and believing, it's not a landscape for small actor, with unbearably high costs and probability of very little revenues.

So my suggestion: learn tools that will gives you power, learn LaTeX to write documents well, it's sound banal but consider a thing: in the past with pen and paper the sign of education is good writing, not we write with computers, good typography is the new sign, LaTeX, TiKz/PGF allow to produce beautiful looking docs very few knows how to make. Learn how to OWN your infra, with desktop tools, not clone of some giants web service.

This base will gives you no money at first and maybe not much excitement but gives you the basis very few now have to going anywhere you want in IT. Notes? Notes means text, the most used tool to store, transmit and transform knowledge, so well, notes like Emacs/org-mode/org-roam are "notes", you can insert code listings, evaluating them live, attach files, handling personal finance with PTA tools like BeanCount or Ledger, full-text-search anything, export to LaTeX or a website, trying to compete against these feature is a giant task asking for years of development, trying to make this software for the masses is the way to push again people toward FLOSS because it became "current" again, profiting from the technically more vast, best and free codebase on the planet without selling "Open Source Enterprise" and with instead of on top and against the community.

Congratulations on building a product. Putting something that works out there in some sort of appealing fashion is hard.

That being said, this is the wrong product to build. I encourage you to spend some time looking at all the ways that commercial AI services are inherently unethical. Furthermore, the use of LLMs in education is incredibly fraught with moral dilemmas. And as others are pointing out—even if you could find a way to use an LLM in a moral fashion as part of academic study, that doesn't seem to be what you're actually promoting.

I wish you luck on a future product that was built ethically.

It's been a long time since I had any school studying to do but just curious: what is the benefit of something that answers questions for you? It seems to me if you don't know the answer you need to review the material not have the answer handed to you.

> Works Undetected

> LIRA works in the background on any webpage.

This is false. If you mutate the DOM on the page, you're trivially detectable. Unless this is meant as a honeypot you should at least warn your users that you're only undetectable as long as the edtech sites don't care to try.

Courtesy of ChatGPT 4o mini:

  const onPopupDetected = (node) => {
    console.log('<lira-popup> element detected:', node);
  };

  const observer = new MutationObserver((mutationsList, observer) => {
    for (const mutation of mutationsList) {
      if (mutation.type === 'childList') {
        mutation.addedNodes.forEach((node) => {
          if (node.nodeName.toLowerCase() === 'lira-popup') {
            onPopupDetected(node);
          }
        });
      }
    }
  });

  observer.observe(document.body, {
    childList: true,
    subtree: true,
  });