[0] https://github.com/ladderlife/autochrome

You might want to give this a try, it dramatically improves Edit tool accuracy without changing the model: https://blog.can.ac/2026/02/12/the-harness-problem/

I think the confusion is that, when I write "model", you read "LLM."

LLMs aren't the only kind of AI model, and they have the limitations Aphyr mentions, for the obvious reasons you're thinking of.

His mistake is thinking that's the only model that exhibits intelligence today, but it's not.

This is the part of the article that will age the fastest, it's already out-of-date in labs.

Just like we have machines that can do "math", and they do so artificially.

Or "logic", and they do so artificially.

I assume we'll drop the "artificial" part in my lifetime, since there's nothing truly artificial about it (just like math and logic), since it's really just mechanical.

No one cares that transistors can do math or logic, and it shouldn't bother people that transistors can predict next tokens either.

But that's a hazy, 20 year old memory.

Not even close.

[0] https://craftinginterpreters.com/

You can (and people do, core.async in Clojure works this way) put entire compilers in macros, macros are just functions that take and return code.

    (filter ds (> year 2008))

I thought that too before I learned Clojure, now I find them equally readable.

Electric Clojure: https://electric.hyperfiddle.net/fiddle/electric-tutorial.tw...

Keeping chat content around for 30 days might as well mean "forever." Anyone at the company can steal your customers chats.

My agreements with customers would prevent me from using any service that did that.

A privacy policy that's at least as good as Vertex.ai at Google.

Otherwise it's a non-starter at any price.