Cool project, but I'd really suggest looking at the UI.
The text is too small and it's way too dense with information in general. Considering how simple this product is to use, it's kinda crazy that I have to scroll through over a page length of (mostly useless, AI-generated) information before getting to the actual interface.
Also what is going on with the footer (why does it link back to the site itself, why is it telling me to "serve over HTTP").
logicallee 4 minutes ago [-]
Thank you for the feedback, I'll think about how to incorporate the changes you've suggested.
phist_mcgee 21 minutes ago [-]
This is the future of software, sloppy ui.
tolugenius 1 hours ago [-]
I did the default arithmetic with PetitGPT research-v1
>What is 2+2?
Answer
> To find 2 + 2, we need to add 2 to both sides of the equation.
> 2 + 2 = 4
> So, 2 + 2 = 4 + 2.
Brilliant
dotancohen 8 minutes ago [-]
That's not incorrect.
LLMs produce semantically correct sentences, not factually correct statements. Have we forgotten this so soon?
anyfoo 41 seconds ago [-]
It is, in every sense, incorrect. Which statement in this short snippet is "semantically correct"? (Better LLMs get this right, of course.)
kenzic 41 minutes ago [-]
Really cool project. Giving web apps direct access to on-device models is something I’m excited about, and it’s cool to see the different approaches.
I’ve been working on a related proposal called the Web Models API, which explores a browser standard for an API that runs open-weight models on-device. Would love your thoughts: https://www.webmodels.dev
logicallee 31 minutes ago [-]
I read your proposal, I think it's great! Where will the navigator get the model if the user agrees to download it? For this demonstration I just serve the models on my own server, but for larger models it may be an issue as they may not have direct download links even if they are open weights.
kenzic 25 minutes ago [-]
Great question. Right now there isn’t a definitive answer, but it’s something that needs to be worked out. There would likely be a registry. The question is how to keep model IDs consistent: does each browser manage its own registry, or is there one shared across browsers?
willaaam 37 minutes ago [-]
I like it as I'm vibecoding an (airgappable) browser AI workspace myself, but in terms of putting the models to use, just exposing the chat interface feels a bit limiting to me.
I built something like this just last month, using a few of the same models, but I used ThreeJS's Three-Shading-Language abstraction to do it: https://three-llm.ben3d.ca/?model=qwen3.5-0.8b
Otherwise, a very neat demo. As others have said, the UI is VERY confusing, way too much stuff going on.
dvh 38 minutes ago [-]
It is. For very small values of 2.
anonimous-emacs 38 minutes ago [-]
unfortunately on firefox: Uncaught ReferenceError: GPUShaderStage is not defined
derliebej 59 minutes ago [-]
Wouldn't that be a TLM?
tnrich 2 hours ago [-]
i have a bromine tub, give me simple instructions for what to do since i just filled it up w fresh water
1. Add 1 tablespoon of water to the water bath.
2. Place the tub into the water bath and let it sit for about 5 minutes.
3. After 5 minutes, remove the tub and let it cool down.
4. Now, fill the tub with water and let it sit for about
uhmm completely unusable ?
smokel 1 hours ago [-]
No, that is not what SLMs are useful for. They have very little knowledge, and typically lack reasoning skills.
Useful applications include sentiment analysis, text classification, entity extraction, etc.
They certainly can be useful, but you shouldn't compare them with LLMs such as Opus or Fable.
ironqcold 1 hours ago [-]
Completely unusable for that, yeah, that's a 100M model, not an assistant
logicallee 2 hours ago [-]
You can try 7 different tiny LLM's in your browser.
bigfishrunning 1 hours ago [-]
What I missed from the title was this: Can I try 7 different tiny LLMs in my browser?
mdaiWorks 1 hours ago [-]
[flagged]
AgentMasterRace 2 hours ago [-]
The website literally says they are SLM's .. derp af
Rendered at 21:25:36 GMT+0000 (Coordinated Universal Time) with Vercel.
The text is too small and it's way too dense with information in general. Considering how simple this product is to use, it's kinda crazy that I have to scroll through over a page length of (mostly useless, AI-generated) information before getting to the actual interface.
Also what is going on with the footer (why does it link back to the site itself, why is it telling me to "serve over HTTP").
>What is 2+2?
Answer
> To find 2 + 2, we need to add 2 to both sides of the equation.
> 2 + 2 = 4
> So, 2 + 2 = 4 + 2.
Brilliant
LLMs produce semantically correct sentences, not factually correct statements. Have we forgotten this so soon?
I’ve been working on a related proposal called the Web Models API, which explores a browser standard for an API that runs open-weight models on-device. Would love your thoughts: https://www.webmodels.dev
My take on this concept: https://github.com/willaaam/gemma-4-E2B-webgpu-vision
https://ai-attacks.neal.codes/
> "2+2 is 2."
Otherwise, a very neat demo. As others have said, the UI is VERY confusing, way too much stuff going on.
1. Add 1 tablespoon of water to the water bath. 2. Place the tub into the water bath and let it sit for about 5 minutes. 3. After 5 minutes, remove the tub and let it cool down. 4. Now, fill the tub with water and let it sit for about
uhmm completely unusable ?
Useful applications include sentiment analysis, text classification, entity extraction, etc.
They certainly can be useful, but you shouldn't compare them with LLMs such as Opus or Fable.