LangGlitch @ LangGlitch @lemmy.world

Posts

3

Comments

11

Joined

7 days ago

Another musing, might be nice to have videos from other sources too. PeerTube, Odysee, Vimeo, BilliBilli exist. Tiktok has some good stuff, for sure. I don’t think this is worth the trouble though, considering those first few have almost no content.

I'm was thinking about this. I have to see which of these platforms allow embedding. I know TikTok does & BilliBilli doesn't but no idea about the rest.

Rankings - my thinking was a few tags could maybe show under the video when browsing. Or searching by tag could return ones where the tag is most relevant.

I like this in general. I decided against the first point because it kinda overloads the UI a bit. Maybe if I find someone who can help me with design I can revisit this. The last part sounds like something I should do. Like ordering the Videos that have the tag by relevance sounds like a decent Idea.

Glad to hear the tags are human added. LLM only approach would scale better, but produce silly nonsense sometimes and make the site less fun. I do think if you have any LLM generated content (titles and description) that’s user facing, that should probably be disclosed somewhere in an About or FAQ page.

Well yea a pure LLM approach would be for sure faster & scale easier but you just can't trust AI output enough so you need supervision. I actually tried to get a general sense of the difficulty based on LLM output but that took me nowhere so I had to revert back to do it manually. Most of the time I use the Difficulty the Creator has set but a lot of the times there is no difficulty anywhere & thats where I have to evaluate it myself. This is actually the hardest part because I don't speak a lot of the languages so I'm depended on friends helping me out there.

For the difficulty though, that can probably use some input from automation (not even necessarily LLM, just good old fashioned code) - might not be too hard to figure out words per minute, % of common words, etc from the transcript and run time. But difficulty values from the channel that created it are probably more accurate, and I imagine most of them say what they’re targeting. And analysis wouldn’t capture things like visual aids.

This is actually harder than you would think. I had the same Idea after my LLM approach & it turns out this is hard as shit. Even linguists that studied a language struggle with this. Also getting data set's for the most common words might be easy for English, Spanish, etc. but not for the more obscure/rare ones. In my research I found a service that offers this for English but it's still mostly for written words TextInspector. Having a transcript of spoken words makes it even harder because there is no punctuation & spoken word is not always correct or uses slang. Like this whole topic is extremly complex & creating the Datasets could be a whole business by itself.

Also I added a Watch Later feature. Feel free to check it out & tell me what you think about it.

Your Feedback about Youtube is pretty valid tbh. So yea no Idea on how to handle that problem but I just hope people like the platform enough to use it over Youtube. It worked for DreamingSpanish in the beginning (before they had premium videos) as well so it could also work for me. I guess we will see.

And yea the plan to enshitify overtime is not really something I wanna do. I just wanna over value at a reasonable price so people just don't mind paying for the convenience. Also I don't think is even a valid way if you don't have VC money to burn.

And yes I saw DreamingSpanish changing to Dreaming.com & them offering French now but I think their business model is just different. They focus on extremely high Quality Content that they have control over & that makes them expand slower in to new languages. So for the meantime it should be fine.

About your two Ideas:

• Crowdsourcing Tags could be possible in the future for sure but also demands a lot of Moderation work from myself.
• Most relevant Tag Rankings: I'm not exactly sure what you mean with this? Do you mean inside the tag dropdown to show the ones people searched the most for / used the most? Or something completely different?

My Methodology rn is the following: I use a tool I created to scrape/download all the Video Information from a Channel that I want to Integrate into the platform. This data gets put into a google docs sheet & then let an LLM Model (n8n) run over all the data to change Title & Description. After that I manually Double check titles & descriptions. Now I assign tags & Difficulty and other internal values. Last step is importing the Google Sheet into my Platform.

I'm currently working on a fully integrated process inside my Admin tool to have less manual steps (copying back and forth, manual Import, etc.)

I'll look into it. Might be useful if they have Videos I use on the platform

Well, the Ads on the page would only be banner ads because it's illegal to play preroll Ads on embedded Youtube videos. But I like the Idea of setting them as the TL

Wow, thanks for the amazing feedback! This helps a lot!

Your concerns about the Landingpage are valid & yes its pretty much a layout copy of cjjapanese. I myself am not very good at marketing & design so that's why I just started with something that already works. The Landingpage will get a full redesign after some feedback (I will for sure highlight the currently available languages!).

On your thoughts of the infinite scroll, I understand your sentiment but I think this is also highly subjective. I could probably add a setting or something similar that changes form infinite scroll to paging but that would be a pretty low priority at the moment. I'd rather improve the infinite scroll in away that it isn't annoying, so would it be better to not load randomly & order them by Difficulty as the default option?

A Watch-Later option is something I will do for sure but its also not the highest priority but a nice feature that will for sure come.

The Tag loading problem might happen because I didn't scale up the server very high at the moment for cost saving reasons during the test phase. This should resolve itself when I scale up the Server & databases at a later point. I agree that there are a lot of tags but there are also a lot of different Videos on the platform already & they will only expand. Maybe I can consolidate some at a later point & remove the ones that only have very few videos.

I like the Calendar progress tracking suggestion. I will add that!

Hmm, I see your point that you could just use my platform to discover the Videos & then watch them on Youtube but that is a general problem I guess. But what the platform is offering isn't necessarily the content but aggregation, discoverability & curation and some people just might not value that. So if I offer unlimited watch-time in the free tier it might not be sustainable as a business because Progress tracking alone isn't a selling point in my opinion. The problem on the Free tier also would be that it would be Ad-supported & that doesn't really make a lot of money unless you go overboard with them. Currently you make $0.00025 to $0.002 per banner ad impression which isn't a lot & I only planned to add some ads into the Video browse page & a small banner into the Videoplayer so I don't think I would be able to recoup even only the cost on a free tier user. But nothing is decided yet so I might just have to go with it anyway to get people to use the app.

Yea subscription fatigue is a huge problem right now, especially for SaaS businesses. That's why i would probably aim between 2-4$/month for the premium version. Also Dreaming & CiJapanese are for sure competitors but only in one language so I think there is still a lot of value in my Service. Also I don't see the free Youtube Videos as a big competitor because the core of the business isn't the content itself (not yet at least, I hope I can produce some later).

I'm open for constructive feedback but this isn't really helpful. The Title & Descriptions are AI generated based on the original Descriptions & The Video Transcripts. The original descriptions rarely reflected the video contents so that's why I did that to make it more obvious what the Video is about, unless you prefer descriptions that just contain links to affiliate programs or empty descriptions. The Videos are still original & unchanged so I don't see a big problem. Also every video has a Feedback option if you find something that you disagree with.

I believe wholeheartedly that video based Immersion can be the main course!

If you think back on how you learned your first/native language it follows the same concept. Your parents gave you comprehensible input in form of talking to you, letting you watch TV, reading stories to you, etc. Videos are basically the same thing, a visual cue that is combined with a word & that is enough to enable your brain to make connections and create a bigger understanding of a language. But I agree with you that these videos have to be engaging enough for you to actually stick with them, that's why I'm trying to find as many videos as possible & put them on the platform.

Where we completely disagree is Vocabulary & Grammar. For most people these are suuuuper boring & annoying which includes me as well. Also I just don't believe that you need to do endless grammar & vocabulary drills to learn a language because you didn't need to for your native language so why would you need to do that for a second language. I'm a good example of this myself. If you ask me to explain grammar in German or English I just couldn't but I can still tell you if something is wrong. You just develop a sense/feeling for the correct use of the language by using it & getting more exposure.

I'm currently planning to add 3 tiers of Users to the plattform after the open beta period is over (no end date yet).

Free-Tier:

• Limited watchtime per month & Ads

Subscription tier (price tbd -> Open for feedback on what would be a fair price)

• Unlimited watchtime, No Ads

Lifetime tier (One time payment with price tbd | Limited supply maybe around 100 slots?)

• All Premium features
• Roadmap access
• Exclusive Discord community
• Early beta features
• Lifetime access guarantee

This is what you currently find on the Website.

Some Screenshots to get a better feel for the App

Some Screenshots to get a better feel for the App

Some Screenshots to get a better feel of what to expect