fi-le

Within the cs.CY category, I only found a slight increase in delays since 2016, that seems to be well within error bars, but it could also be that my sample size was too small.

If you read the article, you'll find that, surprisingly, the delay I was personally observing likely has nothing to do with AI-assisted submissions.

fi-le.net

Thank you for the nitpick, corrected!

Thank you, corrected!

Thank you for the kind words.

Thank you! As the other commenters already figured out, I manually write HTML and use tufte.css with some minor customizations.

What percentage, in numbers?

Evals for programming languages with formal verification. It's not clear how far we are from good coding performance in less popular languages in general, and formal verification has some quirks on top also.

Done, thank you!

Hi, thanks! If someone posts better translations I will update them.

Did anyone get confirmation that the form got sent? There is no feedback from pressing "submit" for me.

Good point. The architectural solution that would come to mind is 2D text embeddings, i.e. we add 2 sines and cosines to each token embedding instead of 1. Apparently people have done it before: https://arxiv.org/abs/2409.19700v2

Two corrections, as written in the post: At least Claude not able to solve the standard levels at all, and community levels are definitely in scope.

At least in this instance, it came from my fleshy human brain. Although I perhaps used it to come off as smarter than I really am - just like an LLM might.

That is the sweetest compliment I could have hoped for, thank you.

I wrote it and am really confused what you mean, I think I'm missing a joke? If not this is serious, it shouldn't be there.

Wow, I guess my hosting provider uses Cloudfare and that setting then.

You're completely right, my argument is fundamentally wrong because it relies on the commutativity, but the embedding matrix obviously does not treat some columns differently than others. Back to the drawing board I suppose. Thanks!

Oh, are you getting a captcha when accessing the site this links to? If so, I didn't know this.

This is a great point, I think I might have been wrong actually. It doesn't really make sense that one row of the embedding matrix is treated differently than another...

You're right, evidently my programming wasn't quite up to the task here. Good to see though that there's demand, so I'll try and make a better version implementing something like you are describing.

I was wondering where the traffic came from, thanks for mentioning it!

It does, we use it as a default. Some possible benefits are that 1) it saves input tokens 2) in theory allows for different variations on a theme, whereas with two seperate prompts you run the risk of repeating one topic.

So glad you like it! If I understand your question correctly, yes, we are also putting together a small library for training small language models. It's not mature at all yet, but can keep up with our progress here: https://github.com/danbraunai/simple_stories_train

We're doing a successor to this, working hard and going public in month or so, hopefully. But HN gets a preview of course: https://huggingface.co/datasets/lennart-finke/SimpleStories

And here's a more interactive explorer: https://fi-le.net/simplestories

You awe absowutely cowwect, a cwassic wookie mistake on my pawt! And thanks ~~~ヾ(＾∇＾)

faint sound of topologists all over the world cheering