Interesting approach to interactive learning. The form-based interaction is a nice middle ground between passive reading and open-ended chat.
One observation: the real challenge with "doom learning" products is retention. People install Duolingo with good intentions, then drop off. Consider adding:
- Spaced repetition (show me this again tomorrow, then in 3 days)
- Micro-commitments (5-minute sessions, not 30)
- Contextual relevance (I just learned 'find' — now quiz me next time I'm actually in a terminal)
The quiz format works well for syntax/commands. For conceptual topics, maybe switch to "explain like I'm 5" mode with the LLM.
Thanks very much for the feedback. If you have any ideas of how to communicate the retention mechanisms please let me know. If you want to discuss further, please leave feedback on the site (you can do this if you're signed in) and mention you are nivcmo from hn and I'll be in touch via email.
An interesting approach, Good luck with it!
A nit to pick: find is not a bash command. You can run it for example from a Windows DOS command line as:
wsl find ...
You can run all Linux commands this way. Also, pretty sure that find's "-o" is the Boolean "or", not "otherwise". (Yet another example of why learning from LLMs is dangerous, I suppose).
I like something here. The interactive - incremental steps of learning or teaching. But having to go through sort of quizes to just get info I need - may not be best for all use cases.
There is a reason chat bots work - it mimics natural human interaction.
But this can be interest pattern - for say AI driven personal tutor for math topic
Lastly - for love of god - pls do something with the UI - all colors and bubbles and I am totally lost just trying to make sense of what is going on. Look at reditt if you just want back and forth thread convo style. Life is simpler that way.
It would be great to be able to kick of a chatbot convo to go deeper on something each time you have answered. Chat for a bit to deepen understanding and read around, then pop back out and continue to the next question when your satisfied you've understood the concept.
Agree on colours. The Electronics topic was white on yellow, completely unreadable.
My feedback reiterates what you're hearing about the cogintive load being unruly. If you want to "beat" doom scrolling, you need your mechanics to be as simple -- quick swipes and taps.
One potential direction, simple cards that are True/False.
If you want to beat doom scrolling, put your phone down?
Directed learning towards some goal is always going to be useful. These replacements for doom scrolling are addressing a surface level issue. Just change your habit to be spaced repetition on flash cards.
I thought this would teach you random facts in one-screen-sized tiles. This doesn't look like doom scrolling. But I like the idea of the user picking a subject, maybe combine both: pick a subject, it gives you facts about it, maybe a tile to ask for which path to take once in a while (swipe left to keep learning about find, swipe right to learn about xargs).
Great idea. It sadly doesn’t work for me, I went to pick a topic and some of the answers were pre-submitted, some of the questions did nothing after clicking “check”, then it just ended. Maybe it’s the HN hug of death?
The example you gave is just so buggy; why do you think that this is worth sharing with the world yet?
The very first question is full of obvious bugs.
You have 'find . -name "notes.txt"' selected, it then says 'You submitted: ls -R | grep notes.txt: find . -name "notes.txt"', then it responds:
'Thanks — your answer looks like it was partially entered.
'You picked find . -name "notes.txt" (good choice). The submission shows an escaped/unfinished string: find . -name \. The correct full command is find . -name "notes.txt", which searches recursively from the current directory for files or directories named exactly notes.txt.'
There seems to be some weird kind of quoting issue going on there. I would fix obvious issues like that before sharing this with the world.
> why do you think that this is worth sharing with the world yet?
It's worth sharing because it's cool, even if it's not perfect yet!
You'll never make every single person on HN happy. But if you share your stuff early and make one person happy at the very least that means you should keep working on it!
Don't let perfectionism get in the way of good enough :]
Show HNs never pleased everyone, and it'd be silly to try, but until recently there was a bit of a "it's not perfect... but the person has spent more time working on this than I have even spent thinking on the problem" kind of expectation whereas now many of them feel like the comments section ends up doing more thought about the submission than was put into refining it.
It'll be really interesting to see where this settles. In the meantime, erring on the side of kindness tends to work best!
Personally, I found this idea cool, and a fresh change from the onslaught of clawdbot posts on this platform. It was enough to make my time on this site a little bit more enjoyable. There's no need to nitpick to the point of bringing down another human for their work.
Sorry, I shouldn't have been that harsh about it; I apologize. Doesn't look like I can delet the comment, though.
Anyhow, I'm just a bit bitter about the onslaught of obviously vibe coded projects that very little effort has been put into. And OP did ask for feedback. But I shouldn't have been so mean about it. I know it can be fun to be able to whip up something quicker than you could before, but I really wish people would spend a tiny bit more effort on it before asking for feedback.
Hey, I appreciate your views (both positive and negative). There actually is a bit of a back story behind it all. I spent a month working on a different version of rebrain, (still available here: https://dev.rebrain.gg). After putting that work in I started to show it to some friends. It was clear from how they responded that it was not as promising as I had hoped. I listened to their feedback and came up with a different idea for LLM-based education (which is the version that's live now). I did vibe code it in about 3/4 days. But I vowed to try to get feedback sooner rather than later, which is why I posted it on ShowHN pretty early in its development. I do want to improve it... so please let me know if there are things which really frustrate you.
I checked the website and you weren't harsh enough. It reads more like a post modern art about vibecoding, some kind of performative art than anything.
I am not a big fan of AI-generated educational content, mostly because it's a great way to confidently learn falsehoods and misconceptions. I would prefer to learn from a reliable and reputable source.
I am also not a big fan of trying to beat doomscrolling. One of the defining properties of doomscrolling is that it is mindless and addicting. The moment you try to create a mindful, healthy alternative, you've already lost. No product will ever beat doomscrolling, only individuals dedicated to their own mental health are capable of clearing this hurdle.
This was a couple of years ago, but I remember using ChatGPT to try and study for a certification by generating quiz questions.
It would always start to make every correct answer option "C" over time, no matter what I tried. Eventually I was so focused on whether or not it was stuck in a "C" loop that I started overthinking all of the questions and wasting time.
Flash forward to testing Sonnet 4.6 recently to try and see if it could effectively teach me something new, I got about 5 prompts in before I had to point out an oversight, and it gave me the classic "you're absolutely right, ignore that suggestion".
This is anecdotal of course, but at least LLMs are helping to build my skills of fact verification and citation checking!
Great idea! I too forget the many switches that the 'find' command can use. Anything that teaches and helps one understand the core concepts of any subject is always a good idea. I'm just not a fan of creating an account and password. I have way, too, many of those. Good luck :)
One observation: the real challenge with "doom learning" products is retention. People install Duolingo with good intentions, then drop off. Consider adding: - Spaced repetition (show me this again tomorrow, then in 3 days) - Micro-commitments (5-minute sessions, not 30) - Contextual relevance (I just learned 'find' — now quiz me next time I'm actually in a terminal)
The quiz format works well for syntax/commands. For conceptual topics, maybe switch to "explain like I'm 5" mode with the LLM.
Good luck!
wsl find ...
You can run all Linux commands this way. Also, pretty sure that find's "-o" is the Boolean "or", not "otherwise". (Yet another example of why learning from LLMs is dangerous, I suppose).
There is a reason chat bots work - it mimics natural human interaction.
But this can be interest pattern - for say AI driven personal tutor for math topic
Lastly - for love of god - pls do something with the UI - all colors and bubbles and I am totally lost just trying to make sense of what is going on. Look at reditt if you just want back and forth thread convo style. Life is simpler that way.
Agree on colours. The Electronics topic was white on yellow, completely unreadable.
One potential direction, simple cards that are True/False.
Directed learning towards some goal is always going to be useful. These replacements for doom scrolling are addressing a surface level issue. Just change your habit to be spaced repetition on flash cards.
This is something else entirely and requires far too much thinking for the label.
The very first question is full of obvious bugs.
You have 'find . -name "notes.txt"' selected, it then says 'You submitted: ls -R | grep notes.txt: find . -name "notes.txt"', then it responds:
'Thanks — your answer looks like it was partially entered.
'You picked find . -name "notes.txt" (good choice). The submission shows an escaped/unfinished string: find . -name \. The correct full command is find . -name "notes.txt", which searches recursively from the current directory for files or directories named exactly notes.txt.'
There seems to be some weird kind of quoting issue going on there. I would fix obvious issues like that before sharing this with the world.
You'll never make every single person on HN happy. But if you share your stuff early and make one person happy at the very least that means you should keep working on it!
Don't let perfectionism get in the way of good enough :]
Show HNs never pleased everyone, and it'd be silly to try, but until recently there was a bit of a "it's not perfect... but the person has spent more time working on this than I have even spent thinking on the problem" kind of expectation whereas now many of them feel like the comments section ends up doing more thought about the submission than was put into refining it.
It'll be really interesting to see where this settles. In the meantime, erring on the side of kindness tends to work best!
Anyhow, I'm just a bit bitter about the onslaught of obviously vibe coded projects that very little effort has been put into. And OP did ask for feedback. But I shouldn't have been so mean about it. I know it can be fun to be able to whip up something quicker than you could before, but I really wish people would spend a tiny bit more effort on it before asking for feedback.
This is far below most other "Show HN" posts and your first message was spot on.
I am also not a big fan of trying to beat doomscrolling. One of the defining properties of doomscrolling is that it is mindless and addicting. The moment you try to create a mindful, healthy alternative, you've already lost. No product will ever beat doomscrolling, only individuals dedicated to their own mental health are capable of clearing this hurdle.
It would always start to make every correct answer option "C" over time, no matter what I tried. Eventually I was so focused on whether or not it was stuck in a "C" loop that I started overthinking all of the questions and wasting time.
Flash forward to testing Sonnet 4.6 recently to try and see if it could effectively teach me something new, I got about 5 prompts in before I had to point out an oversight, and it gave me the classic "you're absolutely right, ignore that suggestion".
This is anecdotal of course, but at least LLMs are helping to build my skills of fact verification and citation checking!