Isn’t this built into MacOS?

Not between Apple IDs. I use a paid product (ironically also called Magic Switch: https://www.magic-switch.com) to switch between my personal laptop and a few corporate laptops I have.

Will give this free one a go, I think.

Why are we quoting a technical opinion made in 2005 as if 21 years of time passing has somehow solidified the opinion? I mean, maybe it has, but that's not how technical opinions work

They just banned algorithmic pricing in seattle grocery stores. What that means and how they can possibly enforce it, I have no idea.

Can't they just do it with personalized discounts and other loyalty programs? That's what everyone's doing around here.

Regulation of predatory pricing practices is a primary function of government.

It's a reach to even say that's a function of government. It's definitely not a primary function. Outside of a few relatively brief failed experiments, it's not historically something that government does at all.

The history of regulating monpolies in the usa is indeed long and sparse.

thats not very capitalist of them.. come on. how is it the free market cant handle something like this?

5000 messages doesn't seem like a lot. Is that per agent or total?

It is total, and you are probably right.

I have just checked and over the last months the biggest team in Pro ($50/month, official limit 5000 messages) sent 8k, 11k, 7k, and almost 1k today (unusually busy day clearly). Right now they have a few dozen agents live. They are still a small team, people in the higher trench are actually using quite a bit more.

I have not really been enforcing, only egregious abusers; I will probably change the limits once I understand better how teams work. I want this to actually be reasonable and sustainable.

[edit] Updated.

We’re currently entering that time and people are quickly learning that empirical evidence is the new output. It’s the difference between “I think the bug is here” vs “I fixed the bug and here’s the evidence I gathered from user telemetry”

Disclosing that you got some info from an AI is way better than not. We’re all using AI in some capacity just be transparent about it. If you didn’t read the findings then say it. As always there’s nuance and it depends

It’s an agent that’s always-on and can do things proactively. It’s not an app so it’s not limited by your device.

Turns out you you just need taste and the time to iterate

This is such a genuinely useful way LLMs can truly help people. A maze of thousands of information-heavy pages distilled into a single input box. A lot of people get stopped short when presented with too much information - it's daunting. Stuff like this, while super boring and obvious and uncool, totally enables people

I agree, although I think one thing they could improve is giving more examples of what you can try, making them clickable to test the prompt yourself and see the result.

I find prompt boxes without many example usages to be sort of a void on the usability side of things. People can feel stuck without some guidance.

yeah I thought the post was going to be satirical