Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

teamchong.github.io

Post reply on HN
Print view View original

21–30 of 65 posts

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#21

Post by thornewolf »

cjbgkagh wrote: post #19
wereHamster wrote: post #9

Earlier quoted context omitted.

CDN wouldn't help much. These days browsers partition caches by origin, so if two different tools (running on different domains) fetch the same model from the CDN, the browser would download it twice.

Did not know that. That sounds extraordinary wasteful, there must be a file hash based method that would allow sharing such files between domains.

it's a security feature. otherwise my malicious site could check for cdn.sensitivephotoswebsite.com and blackmail you if it was cached already

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#22

Post by cjbgkagh »

thornewolf wrote: post #21
cjbgkagh wrote: post #19

Earlier quoted context omitted.

Did not know that. That sounds extraordinary wasteful, there must be a file hash based method that would allow sharing such files between domains.

it's a security feature. otherwise my malicious site could check for cdn.sensitivephotoswebsite.com and blackmail you if it was cached already

It would be nice if there was a whitelist option for non-sensitive content. I stopped using cdn links due to the overhead of the extra domain lookups but I did think that my self hosted content would be cached across domains.

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#23

Post by logicallee »

hhthrowaway1230 wrote: post #4

so multiple of these browser wasm demos make me re-download the models, can someone make a cdn for it or some sort u uberfast downloader? just throw some claude credits against it ty!

>can someone make a cdn for it or some sort u uberfast downloader? just throw some claude credits against it ty!

Okay, I did so. I realize that in your later followup comment you might want something different (like for Chrome itself to cache these downloads or something) but for now I made what you asked for, here you go:

https://stateofutopia.com/experiments/ephemeralcdn/

It's an ultrafast temporary CDN for one-off experiments like this. Should be lightning fast. By including the script, you can include any file this CDN serves.

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#24

Post by faangguyindia »

cjbgkagh wrote: post #19
wereHamster wrote: post #9

Earlier quoted context omitted.

CDN wouldn't help much. These days browsers partition caches by origin, so if two different tools (running on different domains) fetch the same model from the CDN, the browser would download it twice.

Did not know that. That sounds extraordinary wasteful, there must be a file hash based method that would allow sharing such files between domains.

It offers security.

Just like you wouldn't use same table in your system for all users in a multi tenant application.

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#25

Post by cjbgkagh »

faangguyindia wrote: post #24
cjbgkagh wrote: post #19

Earlier quoted context omitted.

Did not know that. That sounds extraordinary wasteful, there must be a file hash based method that would allow sharing such files between domains.

It offers security. Just like you wouldn't use same table in your system for all users in a multi tenant application.

If the file is hashed strongly enough then it can be no other file. I can see how information on previous sites visited can be leaked and how this could be bad but I think whitelisting by end users could still allow some files to be used. E.g. the code for react.

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#27

Post by OsamaJaber »

Small models in the browser are a different optimization problem than small models on a server. On server you chase throughput so you batch. In browser you're stuck at batch size 1, which means kernel launch overhead and memory bandwidth dominate, not FLOPs

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#28

Post by locusofself »

I've had excellent luck using Claude Code to generate "mermaid diagrams" for me, and convert them to .png format headlessly using mmdc/puppeteer. Really helped me out with an engineering proposal I just finished. In past years I would have fumbled around with Visio forever and the result would have been worse.

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#29

Post by walthamstow »

The Gemma models really are amazing. I was on a flight a few days ago and used E2B to do some basic research on the place I was going to, running the model locally on my Pixel 10 Pro. It gave me basically the same as Gemini or ChatGPT would do when I landed

Re: Show HN: Prompt-to-Excalidraw demo with Gemma 4 E2B in the browser (3.1GB)

#30

Post by halJordan »

locusofself wrote: post #28

I've had excellent luck using Claude Code to generate "mermaid diagrams" for me, and convert them to .png format headlessly using mmdc/puppeteer. Really helped me out with an engineering proposal I just finished. In past years I would have fumbled around with Visio forever and the result would have been worse.

And yet people here insist that the height of an llm is not being above to draw a pelican or count letters in a word
Post reply on HN