nivter

> you will need a very domain-specific use for this to be useful imo

The main premise of this idea is how general and widely applicable it is. They also show examples of how it works on images.

A common tokenizing paradigm would be a huge step towards consolidating how different modalities are preprocessed - something I believe is quite useful for intelligence to scale well across modalities.

Tangentially related but spectral graph theory is one of the most beautiful topics I have studied. What's great about graph theory is that it is quite easy to understand but has devilishly hard problems. Ramsey numbers is an example.

This is an interesting concept. The collaborative aspect of it needs to be highlighted and made easier, since IMO its true value will come from crowdsourced data. Another minor feedback: The "Report an error" button currently points to the creator's personal website.

What's interesting to see here is the amount of optimism and goodwill as the premise for these predictions. I wonder at what point did a dystopian outlook of the future take shape.

Wrote an article for someone who doesn't have the context to appreciate the recently disproven Jacobian conjecture, but is curious and knowledgeable enough to understand it.

> The U.S. government has said that all federal agencies will use quantum-resistant cryptography by 2035

I wonder what the current pace and effort of adopting this new cybersecurity paradigm is, and how familiar (AI) agents are with it. And I would assume most countries actively working on it must have amassed encrypted data, not just China and Russia.

Side note: I found the term quantum-resistant instead of quantum-proof a bit amusing. Also it would be better if the article included some references.

Not a fan of subscription hell myself, I plan to use one-time payment for all my products. Implementation wise one time payment is much simpler than setting up smaller payments that cap at a fixed amount.

Automatic differentiation. For any DAG with a scalar output, it allows calculating its partial derivative wrt the input parameters.