Apple introduced Focus modes in iOS 15 as an evolution of Do Not Disturb, letting users filter notifications and even customize Home Screens by context (Work, Personal, Sleep). In iOS 16, Focus became smarter with Lock Screen pairings and filters across apps like Mail, Calendar, and Safari. iOS 17 refined this with more granular notification controls. Taken together, Focus has evolved from muting distractions to a full context-aware filtering system, a model that shows how AI memory could also be partitioned and personalized by mode rather than being “on” or “off.”

That same framing will be essential for AI memory. Not “on” or “off,” but a filter: what memory is relevant in this context? That same framing will be essential for AI memory. Not “on” or “off,” but a filter: what memory is relevant in this context?

One way to achieve this is through a memory interpreter—a layer that sits between your raw personal history and the work context you’re stepping into. Imagine you’ve been doing deep personal research on a topic—reading, journaling, exploring ideas in your own voice. When you shift into a professional setting, the interpreter could filter that knowledge, stripping away casual notes, personal anecdotes, or tone, while surfacing only the relevant facts and references in a format appropriate for work.

In practice, it would act like a translator, allowing the richness of your personal exploration to inform your professional contributions without oversharing or leaking unintended details. It’s not about fusing personal and work memory, but about controlled permeability

I think if you pointed to a random paragraph in anything written by anyone and told them to make it slightly shorter (or longer), they'd probably be able to come up with something better. The best analogy for this phenomenon is when you shake a bin full of different objects. The shakes are arbitrary motions. Or more precisely, they're not calculated to make any two specific objects fit more closely together. And yet repeated shaking inevitably makes the objects discover brilliantly clever ways of packing themselves. Gravity won't let them become less tightly packed, so any change has to be a change for the better.

If you have to rewrite an awkward passage, you'll never do it in a way that makes it less true. You couldn't bear it, any more than gravity could bear things floating upward. So any change in the ideas has to be a change for the better.

Writing that sounds good is more likely to be right for the same reason that a well-shaken bin is more likely to be tightly packed. But there's something else going on as well. Sounding good isn't just a random external force that leaves the ideas in an essay better off. It actually helps you to get them right.

the easier the essay is to read, the easier it is to notice if something catches

the rhythm of good writing has to match the ideas in it, and ideas have all kinds of different shapes. Sometimes they're simple and you just state them. But other times they're more subtle, and you need longer, more complicated sentences to tease out all the implications

when an essay sounds good, it's not merely because it has a pleasing rhythm, but because it has its natural one. Which means you can use getting the rhythm right as a heuristic for getting the ideas right. And not just in principle: good writers do both simultaneously as a matter of course. Often I don't even distinguish between the two problems. I just think Ugh, this doesn't sound right; what do I mean to say here?

The sound of writing turns out to be more like the shape of a plane than the color of a car. If it looks good, as Kelly Johnson used to say, it will fly well.

It's only when you're writing to develop ideas that there's such a close connection between the two senses of doing it well

The way to write something beautiful and false is to begin by making yourself almost believe it. So just like someone writing something beautiful and true, you're presenting a perfectly-formed train of thought. The difference is the point where it attaches to the world. You're saying something that would be true if certain false premises were.

So it's not quite right to say that better sounding writing is more likely to be true. Better sounding writing is more likely to be internally consistent. If the writer is honest, internal consistency and truth converge.

ideas are tree-shaped and essays are linear. You inevitably run into difficulties when you try to cram the former into the latter. Frankly it's suprising how much you can get away with. But even so you sometimes have to resort to an endnote.

Obviously if you shake the bin hard enough the objects in it can become less tightly packed. And similarly, if you imposed some huge external constraint on your writing, like using alternating one and two syllable words, the ideas would start to suffer

There are two senses in which writing can be good: it can sound good, and the ideas can be right. It can have nice, flowing sentences, and it can draw correct conclusions about important things. It might seem as if these two kinds of good would be unrelated, like the speed of a car and the color it's painted. And yet I don't think they are. I think writing that sounds good is more likely to be right. So here we have the most exciting kind of idea: one that seems both preposterous and true. Let's examine it. How can this possibly be true?

You can't simultaneously optimize two unrelated things; when you push one far enough, you always end up sacrificing the other. And yet no matter how hard I push, I never find myself having to choose between the sentence that sounds best and the one that expresses an idea best. If I did, it would be frivolous to care how sentences sound. But in practice it feels the opposite of frivolous. Fixing sentences that sound bad seems to help get the ideas right.