kristopolous

If you're going to be committing a crime, why would you store it in a cloud service?

I checked. Shocked. Here's the models they allow that with

nemotron-3-ultra-free big-pickle north-mini-code-free mimo-v2.5-free deepseek-v4-flash-free hy3-free

Alright.

On the Opencode client it's literally 0. I haven't even signed up for an account. It's my daily driver. 0 is a powerful number

Again if I can get this somewhere else then I'm game.

That offer free inference?

I've written my own. I know they exist.

I don't offer free inference on large models however

That's just a models endpoint. They'll just let you use them unauthenticated with any client you wish?

I'll go check that but this would be fairly shocking

Can't get those generous free quotas from opencode with that.

Opencode offers free models with 200/requests over 5 hours. That's why I use it. It is the only reason I care about.

What's the alternative there? Gemini used to have free tiers. Qwen used to. AMP used to. Ollama cloud used to. Codebuff used to... None of them have those programs anymore

The reason I use it is purely financial. I do not have an employer and I'm writing free software

Edit: pi.dev doesn't have free inference endpoints. That's the constraint.

Cleaner than Japan? That's something...

he's answered this question a few times. It's basically "how was I supposed to have any idea what the implications were?" He said something like "16 bit, 32 bit, 48 bit addressing, it felt all equally improbable. Why would there ever be 65,000 computers on this network?"

The point of this is if AI is solving things that nobody cares about, that's the utility here. It's doing something nobody else wants to bother with

I'll actually put in spelling errors and grammar mistakes intentionally these days to show human

I want this with smaller models as well like Gemma 4 or Qwen 3.6

there's even an emdash in the placeholder.

No. It's quality control. This is a classic clickbait formula headline with 0 backing. I just typed "list 30 papers to get me started in machine learning" into an llm and got 27/30 of these...

This page is an LLM prompt response as a list of jpegs with a fake title. You can probably just add "and prepare it as a webpage with image previews for each" ...

I think we can do better than someone shitposting a sentence into openclaw and getting it to the frontpage.

People on here are actually building 100 billion dollar companies, publishing in prestigious journals, maintaining transcontinental infrastructures with global reach... let's hear from them instead of a mac mini going burr for 15 seconds.

for people wondering:

"Ente Photos is a paid service, but we offer 10GB of free storage. You can also >>clone this repository and choose to self-host<<."

So both forms...

https://github.com/ente/ente

The typo that sometimes got through in official literature still makes me giggle

https://www.google.com/search?q=site%3Acern.ch+%22large+hard...

Help me improve local model performance with petsitter!

It basically exploits the face that time can be traded for intelligence with local models

https://github.com/day50-dev/Petsitter

This is what they want. When they say "small government" they mean "small autocratic ruling party". When they say "personal responsibility" they mean "societal harm burdened on the individual"

When they say "liberty" they mean liberty to oppress others ... I've heard this language my whole life. I know what these people stand for and I've seen it in practice. It's heinous and repulsive.

these days my actual policy is to find whoever is being slandered as a communist and vote for them.

Trump will be called a liberal woke socialist within your lifetime because conservatives will need to distance themselves from him

Less. They'd use congress and the courts.

Next time someone tells you this is the party of free market and small government, I guess you just laugh now?

Why do people always fearmonger China speculatively doing things that the US is actively doing?

you don't think that trump/musk would be underhanded enough to cripple the competition for him to catch up?

So much for the party of small government.

the biggest problem is most ai will be local by 2030. Every future device you buy will have AI compute on it somewhere, built in, like it has on-device floating point.

On top of this, people are constantly coming up with better ways of running models on less special hardware and "good enough" models are now existing for most tasks.

So where does that leave the frontier labs? Drug discovery? Maybe some hard math problems? I mean it's not that big actually...

We're in a brief window where this is profitable, like batch computing was in the 70s. However, once your own device can do it, you're going to start migrating.

I totally remember this site...there were a bunch of themed collection sites of various scripts back then. I'd definitely say this is on the same timeline as dockerhub, npm.org and pypi or at that time, cpan (which still exists of course).

The only consistent things I've heard is volume. You gotta effectively spam and some things stick.

It also has to be cognitively stupid to understand - the least amount of knowledge or suppositions required.

I've found myself on the front page maybe 5 times... Someone else posted my stuff.

I find the algo game to be morally repugnant so I don't play it. I just build things and hope they're useful to the right audiences

https://github.com/apresmoi/glyphcss

I wouldn't call it low effort ... seems to be done over the course of months.

I agree it's absurd that those 4 commits started this morning projects that get huge hype and screaming fanboys, but I don't think this is that.

try it again but give a careful explanation of what a bicycle and a pelican is and how the pelican would sit atop the bicycle. Then give it a reference to the SVG tags you want it to use with documentation.

Here's what I got

https://9ol.es/tmp/pelican.png

with https://9ol.es/tmp/prompt_pelican.txt

using prithivMLmods/VibeThinker-3B-GGUF:Q4_K_M