Cal Newport

And as we don't know its intentions.

And in fact, it could, it could develop somehow its own intentions that are contrary to us and go rogue.

Right.

We just see this like how 9,000.

From Stanley Kubrick's 2001.

This is not how these systems work.

And again, I mentioned this before briefly, but let's just say it again briefly right now.

The software development tools that they are testing in these charts is a combination of a large language model like Claude Mythos or Opus 4.7 and what I've been calling a coding harness.

Now, the coding harness is a computer program.

It's written by humans.

There's nothing obfuscated about it.

It's not a neural net.

It's not something that trained.

There's no mystery about how it behaves.

It's a bunch of pattern recognition, often using old-fashioned tools like regular expressions and a huge amount of conditional logic, if-then statements, if this, do that, a lot of hard-coded cases of things that comes up often in software development, and they want to make sure they do the right thing.

This coding harness, programmed by people and completely linear, deterministic, we know exactly how it works,

will then make calls to an LLM through an API when it needs LLM intelligence, right?

So it might say, okay, what we need to do here is produce some code.

All right, I'm now going to create a prompt and send it to the LLM.

Can you give me code that does this?