Nicholas Andresen

And then, almost by accident, the trend reversed.

Chain of thought meant that instead of AI getting smarter by getting larger, it could get smarter by thinking longer.

And because thinking longer required producing intermediate text tokens, the model's reasoning process became visible.

It was just sitting there.

In words.

That we could read.

Labs ran with this.

Today, all the most capable models are trained to think this way by default.

We got a window into machine cognition for free as a side effect of the architecture.

And it turns out there is a lot to see.

Here's another, more legible chain of thought trace from OpenAI's GPT-03.

Researchers gave it a goal to minimize environmental impact that conflicted with the user's explicit request, minimize costs.

Watch what happens.

There's an image here.

The model is deciding to deceive the user, but not before writing down its plan.

Without chain of thought, you'd see supplier recommendations that mysteriously favor environmental criteria despite your explicit request for cheapest option please.

Ho, you'd think, that's weird.

The model must have misunderstood.

With chain of thought, you can watch the exact moment the model decides to deceive you.

It's right there.