Taylor Mullen

And a lot of the times the answer is no, right?

Context engineering, right?

Yeah.

Totally.

And you see this too.

It's like now a lot of the models will show their thoughts, right, of how they're thinking through what you've asked.

And you'll see the thoughts go through every little iteration of those 3,000 words.

But it wants me to do this.

Yeah.

Yeah, so, like, I think it's not a clear-cut answer for where it falls over.

I think everyone has a different limit for, like, their own workflows for what makes sense for them.

I vary amongst all of them, depending on what I do, right?

I go everything from using a full million to going down to, say, like, 400,000.

I've had a few where I've gone down to 300,000.

But it really, really depends on the workflow itself.

I think one of the really cool things is that, like,

Gemini is so good at it where we have teams internally at Google who are using this and give huge swaths of data for it to pick through.

And it's able to do, like Gemini CLI is able to do just instantaneous work for something that historically would be a week's worth of work.

Wow.

And people get a little scared by that sometimes.