red_hare

> When evaluating the Intelligence Index, it generated 150M tokens, which is very verbose in comparison to the median of 87M.

So their base price is 1/5th of Opus 5.5 per token, but if you want "highspeed" it's 2x that and then I guess it generates 2x the number of tokens as well?

That might suggest that Opus is competitively priced after all.

It reminds me of when everyone was trying to build their own frontend framework. Like "neat, I agree with this in concept, but I don't trust your code or you to maintain this project"

This feels right. It fits the "Assembly to C" style transition of abstraction in that we're going from "code to design of code."

A question I've been struggling with, however, is what are the artifacts that live at this level? Are they design docs? Are they standardized? If I read your design docs, will I understand the code or do I need to "decompile" (use a coding agent to explain) to get back to this level of abstract for me to edit it?

No windshield wiper?

You've clearly never asked Claude for help with plumbing.

It's a humbling reminder that not all fields of knowledge application are verifiable in post-training.

What's your opinion on SynthID Bio? Are you worried about a future where medicine has DRM built-in?

For a local non-coding agent, instruction following and tool use are the most important gains

The difference makes a lot of sense to me.

The phones are watches are primarily sold on annual leases through carriers. And no one is buying them for the chips, it's all camera and form factor.

The macs, on the other hand, can more easily swap between chips in manufacturing. And the form factor is pretty static. So Apple, in a race to have the best chip in the field at any given time, is just releasing them as soon as they're ready.

I agree the whole "m5 max > m6" is confusing, but I think they figure only the nerds who learn the specifics are going to care anyway.

As someone who teaches AI at a university, understanding the basics of how the LLM works is really invaluable to understanding where and how they'll be applied.

You're right that it's probably a little too in the weeds, but it's also a nice clear and fun objective that teaches you the basics. Like building a TODO list in JavaScript to learn webdev or a Gameboy emulator in C++ to learn how a CPU works.

I can't help but respect the dev's self-awareness

When you give those resources to your coding agent, do you give them URLs? Or work with local versions?

I've found a lot of success pointing claude at locally downloaded docs over llms.txt URLs but not sure how to scale the pattern for a bigger project.

15 years of mouse-free professional programming and never in my life have I touched these.

Anyone else catch that he wrote this on an 11-inch MacBook Air (2016 at latest)?

What I like about Marimo notebooks over Jupyter:

1. They're just a python file so they work with python editors

2. There's no hidden state

3. I can import from them

4. I'm not accidentally committing base64 encoded image output anymore