I’m very happy that Anthropic chose not to cave into US Dept of War’s demands but their statement has an ambiguity.

Does this mean they’d be ok to have their models be used for mass surveillance & autonomous weapons against OTHER countries?

A clarification would help.

Do you have more info on video encoding process?

You write:

>We created a model without this tradeoff by training our video encoder on a masked compression objective

And I understand why this would give you more detail per token, but how are you reducing total number of tokens?

Curious - how much did this cost to train?

It generated this: https://paraschopra.github.io/explainers/optical-interferome...

I haven't checked it, but I'm curious about your feedback.

What was the source of inspiration for Claude? I skimmed through the text and it does not look too bad, but devil is in the details and I need more time to go throught the fine prints. One remarks is that Young slit experiment could show what happens with a single slit vs 2

Current prompt is like this:

I want to build a self-contained html/js/css file explainer page as close as possible to this explainer: https://explainers.blog/posts/why-is-the-sky-blue/

What I want you to do is this: - Install playwright and chromium headless to take screenshots of https://explainers.blog/posts/why-is-the-sky-blue/ and interact with the page to deeply understand its style, aesthetics, tone, interactivity, visuals, fonts, etc. - Make comprehensive notes of what you observe so you can implement EXACTLY that when building your explainer - Then on the topic provided below plan to build an explainer with similar length, quality, interactivity, writing style, fun, informative as the article given - produce animations in svg (or otherwise) and interactions as necessary. Similar colour scheme but fun/vibrant/happy. Be very very creative. Act like an expert UI/UX designer who can build stunning explainers. Target it for intelligent hacker-news reader. - Get your plan verified by codex - Produce page one small change at a time. Don't output big chunks in one go. But pay extra attention to number of sections and length of the explained. I want it to be as comprehensive as possible (don't skimp on length) - Keep testing what you produce via playwright on chromium headless.

After you’re finished with index.html, can you check via chromium that all animations, diagrams and interactions that they match with their captions and are visually ok (not too small, large, overlapping, etc.). Sometimes there are factual errors in what the caption or text says and what the diagram suggests.

Topic: diffusion models from first principles

Thank you very much!

I pointed Claude Code towards https://explainers.blog/posts/why-is-the-sky-blue/ , take screenshots and build something like it on the topic provided.

For the LLM explainer, did you point Claude at this one? https://explainextended.com/2023/12/31/happy-new-year-15/ This page Claude assisted page rhymes with that one. Sorta.

I verified the Fourier one and the LLM one. The scaling law one is likely okay too as I long back read the book.

yes, i noticed that occasionally but i'm curious which one did you find is incorrect?

Oh this was just snark.

Yeah, that specific one doesn't work so well but apart from it, does any other example not work?

The Fourier transform audio examples fooled me. The example sounds and slider for them appeared consistent as far as I could tell... but then again I don't know much about Fourier transforms.

Maybe I'm out of the loop but have to say this is the first time I have seen an LLM generate a webpage with working audio widgets.

If you liked that explanation of Fourier transforms, you'll probably like this one: https://www.jezzamon.com/fourier/index.html

yep, i was pretty surprised by audio widgets too.

Yes, the skill is something like the following:

# Codex Verification Skill

Use OpenAI Codex as an independent reviewer via `codex exec`.

## How to Call Codex

*Standard pattern with answer extraction:* ```bash CODEX_OUTPUT=$(timeout 120 codex exec '<your prompt here>. Put your complete analysis inside <answer></answer> tags.' 2>/dev/null)