@theo-t3-gg
Cursor subscription plans for individuals and teams include significant usage of the model with double usage for the.
Massively beating out any Google model. I don't think any are even referenced here.
That in and of itself would have been really useful for this type of thing.
And it looks like it had a transient failure, because testing is hard and the cursor adapter is not as reliable as we.
A big callout here, never use Haiku. Just don't at this point.
Workflows are programmatically defining all of the cool things that you need your sub-agents to do.
The rest here is what I want to talk about now, which is that I taught Claude Code how to use Codex.
The price they launched with was less than half of the price that they had originally planned, likely because again.
It was just weekly limit for all models and then your current 5-hour session.
The partitions should have the data we need though. Can you recover its boot?"
I also have 32 threads on that Z book as I mentioned before.
You might have seen hints in other videos that I've been building my own cloud.
I don't know, but my assumption is not well, because otherwise they would have just went and turned it on.
Different model families reason in all sorts of different ways.
We don't care about any of that during the reasoning step. We only care about the outputs.
Get a nano-texture display. I didn't think they'd be great. They actually are.
This is really cool. Are these models as capable as frontier things from the major labs? No, not at all.
So, why are we putting this stuff other places? Why do I have to mirror the data Stripe should be giving me somewhere.
I wonder if part of that is because Cerebrus is weird and they want this all to work there as well, because as they say.
It keeps the best tools from users, developers, enterprises, cyber defenders, and global partners who need them.
that 85% of the web is suddenly accessible when you use a service like browserbase because the agents can actually.
Think I'm going to leak things that I shouldn't hear, but I don't really care.
Like they can train enough on their gigantic internal code base and somehow the model will be good at these.
It's literally 10 times faster than GitHub Actions for a ton of real-world use cases.
And then threads are the sub-primitive on a post that makes them very easy to interface with.
Have you proven that to yourself yet? Have you proven that the cool models and agents and dev tools we have can't get.
Here's a hot take you might not expect for me. I think it's important that you continue to read your code.
What if I reinvent the framework? What if I build my own runtime?
The problem before was that the range was too hard to do.
If you're missing two, they're not going to come over.
