Grok.

I use both and don't feel they're mutually exclusive.

E.g. if I have some ElasticSearch cluster, I use a skill to describe the data, and if I ask the LLM to write code that queries ElasticSearch but to test it first it can use a combination of skill + MCP to actually run a query.

I think this model works nicely.

Scott Alexander are his first and middle names, and Siskind his last name, or that's what I've understood.

Oh, my beloved TNT2 Ultra.

mine too

One I’ve noticed is download/upload progress.

You’ve been able to do download/upload progress using the Streams API with fetch for more than seven years now. https://developer.mozilla.org/en-US/docs/Web/API/Streams_API

on the FE?

The streams API exists on the FE, you can pipe an upload or download through a TransformStream to monitor progress

> I like the approach of running everything locally. I'm strongly of the opinion that the privacy angle for local models is going to keep getting stronger and more relevant.

In HN circles perhaps. Average Joes don’t care.

I bet if you clearly explained the benefits and tradeoffs, and then gave them the choice, Average Joes would care.

They generally do care, but not enough to change what they do or to do without something they use, like social media.

So many people I know say “I only use Signal to talk to you”, it’s like I’m the awkward one for not using Facebook.

Just think of 8 and 16 bit video console games. Those cartridges were expensive so just how sure they had to be they were bug free before making millions of them?

NGI - Natural General Ingelligence

Astrophagology?

Maybe look at MPE-DASH?