alt Hacker NewsShow HN: HN.watch – Videos of all Hacker News posts
Hi HN, I’m Per, founder of Scrimba (YC S20). We’ve spent the last decade teaching people how to code with an HTML-based video format. We’ve now plugged an LLM into it, so that people can create explainer videos about anything. It’s called “Scrimba Explain”.
To demo this technology for Hacker News, we built HN.watch. It’s like HN, but with explainer videos instead of articles. We create them on-the-fly the first time someone clicks on a link.
While there are obvious visual drawbacks of using HTML instead of diffusion models, there are three big benefits: - Speed: Much faster to generate than pixel-based videos (just a few seconds from click to playback) - Cost: Our cost per video is ~$0.04. (Excluding image generation, which some videos utilize. Quickly blows up the cost) - Easy editing: the above benefits also make AI-assisted editing cheap & fast
Our hypothesis is that if video creation goes from “dollars and minutes” to “cents and seconds”, a bunch of new use cases will be unlocked. Here are some we see already: - A video explanation of every single Pull Request (we do this internally) - Give every page in your internal/extrernal docs a video - Turn a complex article into a video in ~4 seconds (via our Chrome extension) - Course creators can quickly draft lessons before recording the real thing - People also create a lot of personal stuff stories for their kids, wedding invitations, birthdays, etc
The stack is based on an open-source programming language (Imba) created by our CTO, Sindre Aarsæther. It compiles to JavaScript, so it interoperates fully with the npm + node ecosystem. You can learn more here: https://imba.io/
We’ve also built our own sync engine (OP), and a context management system for agents (Q). We feared this would make the LLMs struggle when writing code for us, as neither is in their training data (there’s very little Imba in there too). However, we’ve been pleasantly surprised to see that LLMs actually are really good at our stack. This is probably because the stack is extremely dense. Imba is compact, and so is OP, where a single declaration sets storage, sync, permissions, UI, and what the AI sees. This means there’s no translations between frontend, API, db and JSON where the model can get confused and get things wrong.
Simply said, instead of using React.js, Express, Supabase, and LangChain, we built it all from scratch. Definitely suffering from the “not invented here” syndrome, lol! As for the models, we use Gemini, GPTs, Inworld, ElevenLabs, and a few others.
If you want to try it out, just take your pick: - The Web UI (scrimba.com/explain) - MCP (add it to your coding agent) - ChatGPT Plugin - Chrome Extension
You can find a link to all of the above in our docs: https://docs.scrimba.com/explain/introduction
And finally, a real pixel-based video of the tool: https://www.youtube.com/watch?v=k6rbHmBxSEs
Would love to hear your feedback and if anyone has ideas for other use cases.
PS: I expect quite a bit of pushback from HN for this launch, given how fan of text the HN crowd is. This kind of tool is not for everyone. But there are a lot of people today who prefer videos over text, especially in the younger generations.
Comments
These AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point.
I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright
- Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and timestamp a real voiceover
- can reorder scenes both in code, and using ffmpeg for audio.
- interactive controls during authoring, can ask for micro edits or re-builds
- MP4 export/encoder
- Generates a video from a prompt (obvs)
This is actually quite impressive from an engineer viewpoint. I just have the feeling that the videos quickly become very monotonous and rather boring due to the monotonous AI voices. If somehow you could bring dynamic variation in these videos that would be fantastic.
Please, nobody click on the link to this hn item within hn.watch as it would be even more dangerous than typing 'google' into Google
This looks a good idea to let people choose their preferred medium. I am not into video either, but I turned one of my latest blog article into a video using Claude, since I thought it would be “easy.” I asked it to build the video by screencasting a browser presenting the interactive diagrams of the article and add some titles. It build some kind of recording app for me. It still took me many hours, but I think I would be faster if I redid it. I would pay to have it done faster, but I want to keep control of the text, not have a summary.
The article: https://vincent.bernat.ch/en/blog/2026-spanning-tree-video
The tool built by Claude to make the video: https://github.com/vincentbernat/vincent.bernat.ch/tree/2808...
Btw, we are hiring a new developer to join us in Oslo, Norway. We pay well and give a lot of freedom wrt working from home or at the office (hybrid solution). If getting HTML-based video generation down to 1 cent for 1 minute with 1 second delay, then please email me: [email protected].
Nice concept, but why not generate one video per post rather than re-generating the video for each click per user? The result is going to be the same, and it will be significantly cheaper to run.
Great. Wordpress plugin would work. Get publishers to embed these videos at the top of their own articles. Allow them to tweak/fix/fine-tune them. Accept micropayments and on-demand generation. Readers can pay for better videos or "deep-dives."
This will work for young readers too, illiterates, sensory-impaired and foreigners. All four!!
I like the concept and these explainers. It sounds like this is using a HTML based format to be similar to like a Flash / Shockwave animation to keep data size down.
I wonder what the challenge would be of making these videos more interactive would be? Also I do wonder if there is any research happening in making AI explainers more trustable.
You guys are going to hate this but next up: Each thread in a 10 second explainer and it just autoplays
I can see vertical versions of these doing well on YT shorts or TikTok.
you know what might be interesting? The "HN 10 minute" -- 20 seconds per front page hn story as a podcast, daily.
Love this! I've already used it a bunch to go through some HN posts that I might not have otherwise read.
It's definitely a form of TLDR, but for watching?!
This feels like some kind of parallel to Jev in that. If it is super fast, what other use cases may be unlocked it, as you suggest.
Also, I love the simple, easy to remember domain name, HN.watch!
I don't see an RSS feed.
How does this even reliably read the webpages, since so many of them block bots?
loved scrimba. thanks for building that. was anout to pushback bc of the torrent of show hn sloppy pists but this one is fun.
Did not think I would like that, but really good, simple and easy summary.
I'm an instructional designer, and I think this is awesome!
I'm going to be looking to reproduce this.
It's actually very good...
I like it! I bookmarked it. But I wouldn't pay for it.
This feels like when a decent book is made into a movie, and then the movie does well so someone will take the movie and summarize the plot in a YouTube video. TLDR: this is TLDR for TLDR. Just read more from the source.
This is great - many of us who are technical but not working in hardcore tech probably scroll by quickly on stuff we have never heard of. Getting a quick synopsis like this may drive more traffic and understanding.
Thanks!
I just tried it out - it's pretty cool. The postscript was actually noted in the generated video about this topic, which I find amusing.
I have to say, if HN were to add an AI generated paragraph summary about each link at the top of each comments page, it would probably go a long way to improving the discussions about a lot of topics. The number of people who comment based on the title of a link alone is pretty high, and I'd bet the vast majority of commenters only skim the linked pages anyways. Might as well get everyone on the same page with a quick overview.
> And finally, a real pixel-based video of the tool: https://www.youtube.com/watch?v=k6rbHmBxSEs
"a compressor uses three main organs" @ 2:97
I don't dislike that it's video (because I know people who won't read can't be "made to read" by there not being "nice enough explainer videos"), but this is the kind of stuff that bothers me in both video and text, and greatly. I don't want to rant about it here because it's not specific to your product at all, it's not even specific to LLM, the internet and especially youtube is full of stuff that neither speakers/authors nor audience seem to ever parse. And if you're just downstream of big models you probably can't really influence that. But since you are NIH enjoyers, maybe you could train your own at some point? I don't want to consume such videos, but I do want those who do to have nicer ones, because that'd be good for me, too.
This is pretty cool, I'd want to see the visualizations a little different but that's a personal preference.
Thanks, I hate it.
Kidding, I already sent it to a friend with ADHD who has been struggling to remain anchored to the tech world in any way besides Shorts.
But, culturally, I definitely hate the trend it implies!
Neat. Thank you for sharing.
yo this is wild
I would stick with this. There's huge potential here. I'm not going to lie, I did a video of this, and it was pretty slop. Some of it didn't even make sense and was super irrelevant. That being said, refined, there's really actually some major potential with this idea.
[dead]
This is awesome!
Because we all contain multitudes, I can simultaneously accept that:
1. I hate everything about this because I vastly prefer text over video for the same content, especially AI generated video
2. There are a lot of people for whom video is their preferred medium and so this will be valuable to them.
It's a technically cool project and your cost-per-video is impressively low. Best of luck!