Rendered at 17:07:54 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
demibabs 21 hours ago [-]
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").
post-it 17 hours ago [-]
> The text is too small and it's way too dense with information in general.
The Claude special.
fl0id 15 hours ago [-]
For real. all these dashboards look quite similar
amelius 8 hours ago [-]
Also, they should give some examples of what you can use these Small Language Models for, and what their limits are.
phist_mcgee 20 hours ago [-]
This is the future of software, sloppy ui.
azan_ 18 hours ago [-]
Yes, before LLMs we never had sloppy UIs.
aleksiy123 17 hours ago [-]
To be fair this is worse.
It’s verbose with a layer of looking legit play first glance sloppy UI.
I don’t mind vibe code ui but at least some ui efffort would be nice. Not just 1 shot.
api 16 hours ago [-]
I think your memory of pre-AI UIs is rosy. This is a little below average.
post-it 16 hours ago [-]
We didn't have this kind of sloppy UI. Putting in an extra text field is work, so we mostly had blocks of text and misaligned fields and text in the wrong place.
AI has no trouble churning out code, so AI-generated sloppy UIs have text fields everywhere.
katzenq 7 hours ago [-]
[dead]
logicallee 20 hours ago [-]
[flagged]
askjdfksdbfhk 17 hours ago [-]
>Since this submission has been on the front page of HN for hours now, clearly people like it as it is. I don't think I need to change anything about it.
That's not really how it works. People like it in spite of the bad vibe coded UI. That doesn't mean that the UI is good. The criticism was clearly correct. I don't feel bad about publicly criticizing the UI to your face, either, because it's not like you were the one who designed/created it anyway--by the same reasoning, I don't see any reason to get defensive about it, since you have not invested very much of yourself into it either.
This has become a bit of a pet peeve of mine in general. Over the last six months or so I've been inundated with all kinds of lazy, bad vibe-coded UIs via my normal internet usage. It feels paradoxical in a way, because AI tooling should make it easier than ever to fix obvious problems, and yet UIs have gotten worse.
I have two theories for why this is: (1) usage of AI tooling conditions people into engaging with their creations in a certain hands-off, uninvolved, low-attention surface level way; or perhaps (2) those who care about their UIs were the people who were already creating UIs pre-AI, and so the marginal effect of AI tooling has been to increase UI creation amongst precisely the population who cares the least about what they are putting out.
I've also been developing a very strong personal revulsion towards the Claude default design language, including and especially the gold-on-black color scheme, although I admit that this is entirely by association and not because of its inherent qualities per se.
In this particular case it used to not have any text at the top. Just click a model, chat.
I decided that that wasn't very user friendly. It doesn't tell people what it is. Or how to use it. It doesn't explain any of the concepts or vocabulary.
So I asked it to add those things, above the main interface, including the steps people need to take to use it. I think it did great, and I think the small text sizes with a clear title let people who need it, read it, and people who don't can just scroll down. Even with the text it's 600 words.
I like the effect of what it's done. It's better than I would have done if I had written those intro words myself.
Clearly it resonates with people, this thing has been on the front page of HN for 4 hours and with 110 points is by far the most popular thing I've ever posted here.
Vaslo 5 hours ago [-]
Someone flagged your original comment here, not sure why
logicallee 4 hours ago [-]
They probably flagged it because they thought an LLM wrote my comment, perhaps because of the disconnect between my initial reply and the edit. Together with the whole comment, the first part of my reply sounds like it could have been written by an LLM.
janalsncm 16 hours ago [-]
It isn’t about how small the text is or how easy it is to skip. Humans are not transformers with multiheaded anttention. Human brains do not process one million tokens in parallel. Humans have caloric constraints and will be annoyed if you ask them to process irrelevant information.
Therefore, when showing something to humans, the first thing they see should be the first thing you want them to see. And since this is a demo, the first thing they see should be the demo, with sane defaults, above the fold.
Also, it is likely that no one (including the author) has read this “fine print” because it includes incorrect information. GPT-4 isn’t a frontier model anymore.
TZubiri 18 hours ago [-]
It's clear that this was vibecoded. I'm antivibecoding, but here's a tip.
Don't focus on the actual code or the actual UI. You need to give your model a way to see its output. If it just pumps code, it looks at the code. If you let it look at the rendered UI, whether by manually taking screenshots, or making it so that the agent looks at the browser output automagically (with a webdriver or selenium or puppeteer or a skill or whatever), it will fix whatever issues it sees on itself, and it will never be content with delivering something that looks as bad as this.
langurmonkey 11 hours ago [-]
It's not loading for me on Firefox (v156.0.1, Arch Linux), works fine on Chromium.
Firefox doesn't support WebGPU on Linux, that's probably why.
butz 3 hours ago [-]
There is "Prefer WebGPU" toggle (on by default), but it does nothing. How hard would it be to add simple support test to check if browser has all required capabilities to run your application? I think at least allowing to browse models does not require WebGPU, right?
beschizza 5 hours ago [-]
Smol was the only one to answer a basic question about javascript correctly, but I loved this answer from L20 Edu:
Prompt: I'm writing a vanilla javascript and HTML text adventure game. The player will use the keyboard to switch between screens or to choose storylet options in the main screen. Game is turn-based. What is the the best method in javascript to detect keypresses?"
Answer: I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway,
logicallee 4 hours ago [-]
Thanks for trying it! These models are really tiny, I wouldn't expect them to be able to answer about javascript keypresses. I'm surprised that, as you mentioned, the Smol model was able to answer correctly!
tolugenius 21 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
tecleandor 20 hours ago [-]
GPT-2 124M is terrible...
> what is 2+2?
Answer:
> 3+3? 4+4? 5+6? 7+8?
> Reply ~18000 0 ~10 min 2 By : 1-1: I'm a beginner. 3x2 is my best option, but if you're not sure about the other options then just go for it and try again
krackers 20 hours ago [-]
It's not instruct tuned looks like? It's closer to a base model rather than a chatbot.
logicallee 19 hours ago [-]
That one is a 2019 model :) Years before the ChatGPT public preview.
logicallee 19 hours ago [-]
GPT-2 is an interesting one because it is a February 2019 model. (You can see some information about it below the card if you click on the card.)
That was 2-3 years before the big "ChatGPT moment" (the highly coherent ChatGPT research preview was released in November 2022, I think it was ChatGPT 3.5). Back in 2019 the models really were not producing very coherent output. Now you can see it for yourself right in your browser :) Everything has come a really long way since then!
anyfoo 18 hours ago [-]
I've been playing with it for a bit, and I'm a tiny little bit surprised that they decided to continue pursuing that direction of research at all. What I'm getting from it looks like it could just be arbitrary sentence and paragraph fragments from the Internet, pasted together Markov-chain like.
I'm not sure I would have ever believed that something useful would come out of it, yet here we are.
wyrdcurt 10 hours ago [-]
Not sure how you're prompting it but remember that it's not trained for chat or instruction following, it simply takes the text given to it and tries to continue it. Give it the right prompt structure, and it can (at least sometimes) output coherent completions, far more often than you'd see in a Markov-chain. Also, this version is more or less equivalent to the smallest version of GPT-2; the largest version was 1.5 billion parameters and was much more likely to generate impressive (at the time) output.
The assumption that LLMs would always need sophisticated inputs to generate useful outputs is where the term "prompt engineering" came from. Now that idea is basically dead. Absolutely wild how far these models have come in less than a decade!
anyfoo 4 minutes ago [-]
That is insightful, thanks. I didn’t start caring about models until very late, so I genuinely thought GPT-2 was only a single tiny model originally.
And I now tried using it more as a “text completer”, and results are much better.
kasumispencer2 15 hours ago [-]
Sounds about right about something that's 124M. I trained one myself a few weeks ago and it's about the same level of being terrible.
> how would you compare your capabilities to that of claude fable 5.1 by anthropic
> Comparing your capabilities to that of claude fable 5.1 would be very similar. Both are stories about a clown who is a cunning and manipulative animal. They both have problems and challenges, and they face challenges to overcome them. However, they have different goals and approaches. The clown
I think that tells you all you need to know.
Reviving1514 17 hours ago [-]
That's hilarious. At least the smaller model is more self aware!
touchme 9 hours ago [-]
> Is a cat an animal? Answer yes or no.
>> Cats are not animals. Cats are warm-blooded animals that have a backbone and a heart. They are not mammals.
Good job PetitGPT research-v1.
boonzeet 8 hours ago [-]
"What's the capital of South Africa?"
"Bloemfontein".
"No, it isn't. There are 3 capitals"
"China, India, Russia."
Small LM trained on Tiny Stories. My first goal was to get people to see tokens from the model ASAP, the second was to demo Tiny Stories for those who may be unfamiliar. Oh and play with ternary models. https://arxiv.org/abs/2305.07759
There's larger QA model on the same page too.
logicallee 12 hours ago [-]
Interesting project, thanks for sharing.
tcgv 4 hours ago [-]
I had fun with this. Reminds me of the old prompt-engineering days.
[Me]
hi there
[PetitGPT]
Hello! How can I help you today?
[Me]
how much is 2+2?
[PetitGPT]
2+2 is 2.
[Me]
Are you sure?
[PetitGPT]
Yes, I would be happy to help you with that.
[Me]
well, you're wrong.
[PetitGPT]
The answer is not to be taken as a complete statement.
The main points are not necessarily true or accurate.
[Me]
Try again, how much is 2+2?
[PetitGPT]
To find the answer to this question, we need to consider
two numbers: 2 and 2.
We know that 2 is equal to 2 + 2.
We also know that 2 is equal to 2 + 2 + 2.
So, 2 + 2 + 2 = 2 + 2 + 2 +
[Me]
Let me rephrase it: two plus two equals...
[PetitGPT]
Two plus two equals two + 2 equals four.
Surac 47 minutes ago [-]
Seems the models only support English. Questions in German are just echoed
not2b 15 hours ago [-]
Amusingly limited: I asked SmolLM2 360M Instruct
"What is the population of California?"
It replied
"California is the third-largest state in the United States, with a population of around 153 million people. It is also the most populous state in the United States, with a population of around 325 million people. The state is also the most populous in terms of GDP, with a GDP of $1"
But very fast, despite the lack of a decent GPU.
wewtyflakes 15 hours ago [-]
Prompt for PetitGPT research-v1: "How much wood would a woodchuck chuck if a woodchuck could chuck wood?"
Response: "A woodchuck would chuck wood if it could chuck it. The woodchuck's chucking action is a form of "chucking" or "chucking in" which is a behavior that allows it to extract nutrients from wood. The woodchuck's chucking action is a form of "chucking" because it is a form of "chucking" that allows the woodchuck to extract nutrients from wood."
I chuckled.
FearNotDaniel 2 hours ago [-]
I'm never letting any of these models bake me an apple pie.
It's a cool idea. I'm on my phone now (going to sleep soon), a few of the demos didn't boot on this device. I'll check from desktop tomorrow.
logicallee 12 hours ago [-]
I tried the Python and SQLite modules on desktop Chrome and got similar errors for both. For Python:
Error: CPython engine could not load (Failed to fetch dynamically imported module: https://sonistellar.com/lab/vendor/pyodide/pyodide.mjs). Check the network, then close this tile and re-boot to retry. — press reset or back to menu
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 20 hours 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 20 hours 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?
logicallee 19 hours ago [-]
Since you're asking for some kinds of permissions anyway, you could ask if the user is willing to also seed the model, p2p. (However, seeding files is not as popular as it used to be, many residential Internet connections don't have good upload.) If you have the capacity for it, your site webmodels.dev could act as a tracker and initial seed for any models. Then it could be the one central registry. It might get to be too much for you though, a lot of the open weights models are huge.
kenzic 19 hours ago [-]
Interesting idea. I hadn't considered that. Thanks
Schlagbohrer 6 hours ago [-]
Every model I just tried in here gave me very nonsensical hallucinations, or immediately fell into a loop. Not the best examples of what Petite GPTs (as one is called) can do, I hope.
logicallee 4 hours ago [-]
Could I ask what browser, operating system, and GPU you use? In my testing they do not fall into a loop, maybe there is an error that affets how it's being run on your device.
moooff 11 hours ago [-]
I did a WebGPU-based HTML Single-File Chat Application even for larger models. It just depends on your machine. It is cool to show people what can be done on their machines without installing anything. It also works in air-gapped environments.
Thanks for sharing. I tried the online demo, which downloaded the model but, unfortunately, couldn't start it. (It says " Invalid magic number
Make sure your local server is running and CORS is enabled.")
moooff 5 hours ago [-]
Thank you for testing. i just checked it works with Chrome.
FireFox seems broken in the current Version i.e. i can reproduce the bug. Working on it.
Which browser do you use?
logicallee 4 hours ago [-]
I think you've fixed it! I just tested it, now it works. (In both Chrome on Windows with NVidia 1060 gpu w/ 6 GB vram, which is what it wasn't working on yesterday, and on Safari on 2026 Mac Mini M4 with 24 GB of RAM. The former is pretty slow, around 1 tok/sec, the latter is fast at 18 tok/sec.)
moooff 4 hours ago [-]
Yeah, I found a bug during model load occurring with Firefox and low VRAM machines. It is fixed now, thanks!
The 1060 is unusually slow. The Mac mini sounds about right. Have fun playing around and sharing. With the more VRAM of the mini you can also run Qwen 3.8 27b :)
I really like to showcase this to non-tech people to show what their home machines already can do WITHOUT INSTALLATION in an air-gapped scenario! And given all the recent fuss, we should not trust the big providers at all with important data.
brinepot 12 hours ago [-]
Pretty neat how far these small models have come. Running them locally in the browser feels like magic for quick experiments.
philipallstar 7 hours ago [-]
> What is the capital of south africa
> Victoria is the capital of South Africa.
> What is the capital of south africa. It's not Victoria.
> Victoria is the capital of South Africa.
They're coming for your job!
hbroom 12 hours ago [-]
Ran a few of these, and the speed for in-browser execution is wild. Perfect for quick demos without a backend.
Mbarley 13 hours ago [-]
Impressive how much you can do locally now. Was expecting much slower inference but it's surprisingly snappy.
Rexxar 14 hours ago [-]
Very interesting but on a naming perspective what is a "micro large" model ?
willaaam 20 hours 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.
And after loading it, with an NVidia 1060 GPU (6 GB RAM) on Windows it failed with "Failed to load: No supported WebGPU variant for com.xenova.gemma4.DenseGemv; rejected sgma".
In Safari on a 2026 Mac Mini M4 with 24 GB of RAM it failed with "Failed to load: JSON Parse error: Unexpected EOF".
The idea is pretty cool though!
willaaam 18 hours ago [-]
Huh, weird! It doesn't work in Firefox, but I test on Safari (M5 Max) and Chrome (Linux, Arc B580). I don't have access to NVidia or AMD hardware myself unfortunately, though friends confirmed both as working.
Sorry. That shouldn't happen. It doesn't use a lot of memory and only uses WebGPU in the normal way. What version of macOS and Safari did you use, and what is your hardware, please?
bhouston 21 hours ago [-]
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
sourweasel 18 hours ago [-]
I would recommend adding the MiniCPM5-1B model. Surprisingly coherent for a 1B model and performs well. On my pixel 9 I get 33 tok/s on CPU. On GPU I get about 26 tok/s but prefill jumps to nearly 500.
logicallee 19 hours ago [-]
Awesome! I tried it and after loading (which took a while as it is a large model) got 12 tokens/second and very coherent output. Great demonstration.
micw 19 hours ago [-]
It's LLMs, not LLM's ;-)
logicallee 18 hours ago [-]
Thanks. Unfortunately it's too late to change the title!
d3Xt3r 17 hours ago [-]
Maybe we should just call them SLMs instead of LLMs...
jellyfiz 21 hours ago [-]
Similarly, if someone wants to hack some LLMs in their browser and burn some cycles, please feel free to try to break them here:
Otherwise, a very neat demo. As others have said, the UI is VERY confusing, way too much stuff going on.
allenu 11 hours ago [-]
Using the same model, I asked it what 2 + 2 is and it said "2 + 2 is 2 + 2" which is not wrong.
Other questions and answers were mixed:
How many cards in a deck?
> A deck of cards contains 52 cards.
How many cards in a deck if I remove all Queens from the deck?
> If you remove all Queens from the deck, there are still 52 cards in the deck.
dvh 20 hours ago [-]
It is. For very small values of 2.
rvz 20 hours ago [-]
Nothing on this site actually works.
logicallee 19 hours ago [-]
What browser are you using? I tested it on Windows, Mac, and iPhone. I tested it in Chrome, Firefox, Edge, and Safari. Everything works on the three machines and phone I tested it on.
(It's a little bit slow at the moment - you have to wait a few seconds for the models to load - as it's currently on the HN front page. The server is on a 1 gigabit unmetered network connection so it can serve all the weights - around 600 megabytes - to one person every few seconds, there are several concurrent users now.)
fragmede 19 hours ago [-]
serve the models via CDN?
anonimous-emacs 20 hours ago [-]
unfortunately on firefox: Uncaught ReferenceError: GPUShaderStage is not defined
I tested it on Firefox on windows, version 156.0.1 and didn't get that error.
What version of Firefox are you using and what is your operating system and graphics card, please? Can you also try it without WebGPU? (Reload the page and uncheck "Prefer WebGPU" and try a prompt.)
ad_fontes 17 hours ago [-]
Same issue. Latest version of Firefox 156.0 on Ubuntu GNOME. AMD Radeon 860M.
Unticking the WebGPU checkbox and reloading didn't do anything.
logicallee 17 hours ago [-]
This is a difficult one for me to fix since I don't have a Radeon GPU. I'll see if there is anything I can do tomorrow.
cwnyth 15 hours ago [-]
I got the same error with an Intel Iris. I'm using Firefox on Fedora Gnome. "Prefer WebGPU" also didn't fix it.
derliebej 21 hours ago [-]
Wouldn't that be a TLM?
agnishom 15 hours ago [-]
Yeah, or a μLM
voxmastery 8 hours ago [-]
interesting
logicallee 22 hours ago [-]
You can try 7 different tiny LLM's in your browser.
bigfishrunning 21 hours ago [-]
What I missed from the title was this: Can I try 7 different tiny LLMs in my browser?
tnrich 21 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 21 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 21 hours ago [-]
Completely unusable for that, yeah, that's a 100M model, not an assistant
mph1027 11 hours ago [-]
[flagged]
fuckyah 3 hours ago [-]
[dead]
hajjamixcv2012 19 hours ago [-]
[flagged]
mreevestools 12 hours ago [-]
[dead]
mdaiWorks 21 hours ago [-]
[flagged]
anyfoo 19 hours ago [-]
[dead]
WarcrimeActual 3 hours ago [-]
[dead]
AgentMasterRace 21 hours ago [-]
The website literally says they are SLM's .. derp af
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").
The Claude special.
It’s verbose with a layer of looking legit play first glance sloppy UI.
I don’t mind vibe code ui but at least some ui efffort would be nice. Not just 1 shot.
AI has no trouble churning out code, so AI-generated sloppy UIs have text fields everywhere.
That's not really how it works. People like it in spite of the bad vibe coded UI. That doesn't mean that the UI is good. The criticism was clearly correct. I don't feel bad about publicly criticizing the UI to your face, either, because it's not like you were the one who designed/created it anyway--by the same reasoning, I don't see any reason to get defensive about it, since you have not invested very much of yourself into it either.
This has become a bit of a pet peeve of mine in general. Over the last six months or so I've been inundated with all kinds of lazy, bad vibe-coded UIs via my normal internet usage. It feels paradoxical in a way, because AI tooling should make it easier than ever to fix obvious problems, and yet UIs have gotten worse.
I have two theories for why this is: (1) usage of AI tooling conditions people into engaging with their creations in a certain hands-off, uninvolved, low-attention surface level way; or perhaps (2) those who care about their UIs were the people who were already creating UIs pre-AI, and so the marginal effect of AI tooling has been to increase UI creation amongst precisely the population who cares the least about what they are putting out.
I've also been developing a very strong personal revulsion towards the Claude default design language, including and especially the gold-on-black color scheme, although I admit that this is entirely by association and not because of its inherent qualities per se.
I decided that that wasn't very user friendly. It doesn't tell people what it is. Or how to use it. It doesn't explain any of the concepts or vocabulary.
So I asked it to add those things, above the main interface, including the steps people need to take to use it. I think it did great, and I think the small text sizes with a clear title let people who need it, read it, and people who don't can just scroll down. Even with the text it's 600 words.
I like the effect of what it's done. It's better than I would have done if I had written those intro words myself.
Clearly it resonates with people, this thing has been on the front page of HN for 4 hours and with 110 points is by far the most popular thing I've ever posted here.
Therefore, when showing something to humans, the first thing they see should be the first thing you want them to see. And since this is a demo, the first thing they see should be the demo, with sane defaults, above the fold.
Also, it is likely that no one (including the author) has read this “fine print” because it includes incorrect information. GPT-4 isn’t a frontier model anymore.
Don't focus on the actual code or the actual UI. You need to give your model a way to see its output. If it just pumps code, it looks at the code. If you let it look at the rendered UI, whether by manually taking screenshots, or making it so that the agent looks at the browser output automagically (with a webdriver or selenium or puppeteer or a skill or whatever), it will fix whatever issues it sees on itself, and it will never be content with delivering something that looks as bad as this.
Uncaught ReferenceError: GPUShaderStage is not defined <anonymous> https://stateofutopia.com/experiments/microllmlab/engine/web... webgpu-metal.js:24:17 <anonymous> https://stateofutopia.com/experiments/microllmlab/engine/web... [MicroLLM lab] App loader failsafe triggered after 6s microllmlab:55:21
Prompt: I'm writing a vanilla javascript and HTML text adventure game. The player will use the keyboard to switch between screens or to choose storylet options in the main screen. Game is turn-based. What is the the best method in javascript to detect keypresses?"
Answer: I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway, I'm a good player. Anyway,
>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
That was 2-3 years before the big "ChatGPT moment" (the highly coherent ChatGPT research preview was released in November 2022, I think it was ChatGPT 3.5). Back in 2019 the models really were not producing very coherent output. Now you can see it for yourself right in your browser :) Everything has come a really long way since then!
I'm not sure I would have ever believed that something useful would come out of it, yet here we are.
The assumption that LLMs would always need sophisticated inputs to generate useful outputs is where the term "prompt engineering" came from. Now that idea is basically dead. Absolutely wild how far these models have come in less than a decade!
And I now tried using it more as a “text completer”, and results are much better.
LLMs produce semantically correct sentences, not factually correct statements. Have we forgotten this so soon?
> Give me a recipe for soup.
> Here is a recipe for soup:
> Saffa-Cake-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-Sweet-
> Comparing your capabilities to that of claude fable 5.1 would be very similar. Both are stories about a clown who is a cunning and manipulative animal. They both have problems and challenges, and they face challenges to overcome them. However, they have different goals and approaches. The clown
I think that tells you all you need to know.
Good job PetitGPT research-v1.
"No, it isn't. There are 3 capitals" "China, India, Russia."
Small LM trained on Tiny Stories. My first goal was to get people to see tokens from the model ASAP, the second was to demo Tiny Stories for those who may be unfamiliar. Oh and play with ternary models. https://arxiv.org/abs/2305.07759
There's larger QA model on the same page too.
"What is the population of California?"
It replied
"California is the third-largest state in the United States, with a population of around 153 million people. It is also the most populous state in the United States, with a population of around 325 million people. The state is also the most populous in terms of GDP, with a GDP of $1"
But very fast, despite the lack of a decent GPU.
Response: "A woodchuck would chuck wood if it could chuck it. The woodchuck's chucking action is a form of "chucking" or "chucking in" which is a behavior that allows it to extract nutrients from wood. The woodchuck's chucking action is a form of "chucking" because it is a form of "chucking" that allows the woodchuck to extract nutrients from wood."
I chuckled.
Error: CPython engine could not load (Failed to fetch dynamically imported module: https://sonistellar.com/lab/vendor/pyodide/pyodide.mjs). Check the network, then close this tile and re-boot to retry. — press reset or back to menu
For SQLite:
Error: SQLite engine could not load (GET https://sonistellar.com/lab/vendor/sqlite/sql-wasm.js -> HTTP 404). Check the network, then close this tile and re-boot to retry. — press reset or back to menu
FreeDOS loaded though, Snake and Tetris were fun!
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
https://github.com/moooff/HermitUI
FireFox seems broken in the current Version i.e. i can reproduce the bug. Working on it.
Which browser do you use?
The 1060 is unusually slow. The Mac mini sounds about right. Have fun playing around and sharing. With the more VRAM of the mini you can also run Qwen 3.8 27b :)
I really like to showcase this to non-tech people to show what their home machines already can do WITHOUT INSTALLATION in an air-gapped scenario! And given all the recent fuss, we should not trust the big providers at all with important data.
> Victoria is the capital of South Africa.
> What is the capital of south africa. It's not Victoria.
> Victoria is the capital of South Africa.
They're coming for your job!
My take on this concept: https://github.com/willaaam/gemma-4-E2B-webgpu-vision
https://willaaam.github.io/gemma-4-E2B-webgpu-vision/
And after loading it, with an NVidia 1060 GPU (6 GB RAM) on Windows it failed with "Failed to load: No supported WebGPU variant for com.xenova.gemma4.DenseGemv; rejected sgma".
In Safari on a 2026 Mac Mini M4 with 24 GB of RAM it failed with "Failed to load: JSON Parse error: Unexpected EOF".
The idea is pretty cool though!
Going to debug tomorrow!
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.
Other questions and answers were mixed:
How many cards in a deck? > A deck of cards contains 52 cards.
How many cards in a deck if I remove all Queens from the deck? > If you remove all Queens from the deck, there are still 52 cards in the deck.
(It's a little bit slow at the moment - you have to wait a few seconds for the models to load - as it's currently on the HN front page. The server is on a 1 gigabit unmetered network connection so it can serve all the weights - around 600 megabytes - to one person every few seconds, there are several concurrent users now.)
Adding a warning about it could help.
What version of Firefox are you using and what is your operating system and graphics card, please? Can you also try it without WebGPU? (Reload the page and uncheck "Prefer WebGPU" and try a prompt.)
Unticking the WebGPU checkbox and reloading didn't do anything.
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.