logicallee

ok. I withdrew my comment.

[comment withdrawn]

>Also, the Web is already open source

Maybe. What does the license/signed contract if you have one say?

This is really cool! Thanks for sharing.

The second time I read the output I pay for, some of the words are modified to say the opposite. Is there a map of the hidden global labor powering that?

>So it looks like $2T is indeed the target

What do you base that on? (Did you see any reference to that in the linked document or anything published by Anthropic)?

>the market for their valuation is just not there imo

I tried to look for the valuation in the linked document, did you see it or any reference to a valuation elsewhere in anything published by Anthropic? what is "their valuation" that you refer to?

it's a zero dollar company. OpenAI is a virus. It's a liability. The code almost certainly contains some trivial backdoors, since their entire infrastructure is backdoored.

Edit: look at this crap for example:

https://github.com/openai/openai-cli/blob/main/scripts/run

(just the first file I looked at.) it's obviously half of a backdoor. Some other process somewhere happens to give the other half.

openai is a joke, they can't even keep their servers running.

Google used to be the laughingstock but now it's openai.

last place by far.

This was very fun! I enjoyed playing it. Thanks for sharing.

What do you mean "I can't fly it"? You built a drone and only someone else can fly it?

Cling and Clop look pretty cool, thanks for sharing these projects.

>My local llm running on my eight year old gpu and ten year old pc is powered by hydroelectric dams.

how do you still have a job?

This was a ton of fun! I tried it on an iPhone 13. Worked perfectly. I loved the UI/UX and also it was awesome to be able to select chords easily. Sounds fantastic. Feature suggestion: there's a part of it that on a physical guitar can be tapped with the palm (it's shown visually in the dark/red overlay; you may need to zoom out to see it), pressing there could produce a percussive thud.

>Reliably cheap prices

do you have to pay those cheap prices eventually or can you just accrue an unlimited amount of overdue charges?

You mention "most of them" were not generating good recipes. Did any of them give you a usable recipe?

I've tried to fix this, please check again. Thank you.

Thank you. I've tried to fix this, could you please check again?

I've tried to fix this, please check again, thank you.

Great, thank you for making it and also the fixes!

I've tried to fix it, let me know if there is still an issue.

I've tried to fix the Firefox on Linux issue, can you check again? Firefox doesn't have WebGPU enabled by default on Linux so you will have to use the wasm fallback which is slower.

I've made it more clear what parts are optional reading. summary of my changes here: https://news.ycombinator.com/item?id=49897068

All right, I've made some of the requested changes, summarized here: https://news.ycombinator.com/item?id=49897068

I've thought some more about your feedback, since other replies gave the same feedback. At the same time, I didn't want to remove the "mostly useless" information since clearly it was useful for a lot of people! The submission was on the front page of HN (often in the #3 or #4 spot) for 12 hours and last I checked generated more than 300,000 requests from 36,000 unique IP's (on an ordinary 2-day period there are around 1,600 unique IP's) and people downloaded 600 GB of models, including 8.5k downloads initiated for the first model (3,000 of which were completed and 5.5k of which did not wait for it to complete, since download was a little slow due to the high number of concurrent users.)

So, clearly, the presentation format resonated with a lot of people. Therefore, I kept the presentation but put a tl;dr in enormous can't-miss-it shimmering font at the top. I marked all the "dense information" you mentioned as "Optional reading" (it's a lab after all, there should be a reading for it) and increased the font size.

I removed the parts of the footer that you said didn't make sense. The page isn't on the front page anymore so I don't know if people would like the changes or not, but I've changed the page layout in response to your feedback.

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.

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.

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!

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.)

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.")