Andrew Feldman

And that's the simplest way.

And that's the simplest way.

The reason inference is going through the roof is because everybody's using AI.

The reason inference is going through the roof is because everybody's using AI.

A task that you kicked off, it starts a bunch of little threads and each of those asks queries.

A task that you kicked off, it starts a bunch of little threads and each of those asks queries.

And each of those queries deliver results that are the input to other queries.

And each of those queries deliver results that are the input to other queries.

So you've got a cascade of queries that is going on.

So you've got a cascade of queries that is going on.

It's wild.

It's wild.

And each of those requires more compute.

And each of those requires more compute.

And so you've got 20 different queries being kicked off.

And so you've got 20 different queries being kicked off.

Each query asks 20 queries.

Each query asks 20 queries.

Each one of those requires 10 or 15 or 20 seconds to get done in traditional computing.

Each one of those requires 10 or 15 or 20 seconds to get done in traditional computing.