Reverse engineering us

From recorded future news and PRX, This is click here. People are using AI to study us now. Our choices, our emotions, our impulses. The hope is if a machine can model human behavior, it might help explain it. But there's a problem. To judge whether a machine is getting us right. we need to know how our own minds work, and we're not there yet. For example, we can't fully explain how the brain produces thought, or language, or feeling.

So in a way we're asking machines to solve a mystery we haven't solved ourselves. And what they're coming up with might change how we think about thinking. From recorded future news and PRX, this is Click Here, a podcast about the people making and breaking our digital world. This week, a neuroscientist who went looking for answers in the brain. And found them somewhere else? Machines.

I am interested in how language works and suddenly these um large language models producing language that was incredibly well formed. That's after the break. Stay with If you're looking for a daily guide to cybersecurity news and policy, sign up for the Cyber Daily from recorded future news.

It serves up the day's most interesting and important cyber stories from our sister publication The Record and then aggregates all of the big cyber stories you might have missed from news outlets around the world. Just go to therecord.media and click on Cyber Daily to get all you need to know about the world of cybersecurity right in your inbox. For most of modern history, scientists studying the human mind have faced a frustrating problem.

You can observe how a person thinks, you can measure it, but you can't easily experiment on it. You can't extract a piece of a human brain and tweak it just to see what happens. And that's been the bottleneck, not just observing the brain, but testing it. But one scientist thinks she's found a way around this. Doctor Evelina Federenko. Go this way and turn that and then. Okay, thank you very much. I visited her lab at MIT last fall.

Hi, I'm Dina Temple Rest. Very nice to meet you too. The first thing I noticed when I walked into her office was the unusual decor. On a shelf above her desk sat two jars. I squinted to make sure I was seeing it right. They're just brains and jars? Yeah. Inside each jar was a brain. A human brain. And are there special kinds of brains? No, they're mostly people who donate their brains for dissection for like medical classes.

Which is one way scientists have tried to understand the brain for generations. You have to wait until someone dies to study it. Then you can slice it and map it, and compare one brain to another. The problem with that, of course, is that it doesn't necessarily tell you much about how thinking works in real time. And that's the puzzle Ev has spent most of her career trying to solve. Now I'm a neuroscientist at MIT at the McGovern Institute for Brain Research.

Though everyone on Earth has a brain, many of its secrets remain out of reach. The human brain contains about eighty-six billion neurons, each one connected to thousands of others. It has a quadrillion synapses. That's a one with fifteen zeros. The result is a network so complex, scientists still don't fully understand how thinking actually works.

Nev is trying to change that. Her research focuses on how the brain processes thoughts and language, two things that people tend to assume are one and the same. It's very easy to conflate them because that's what an effective communication system does. It allows us to share thoughts, right? For centuries, philosophers and linguists, from Plato to Noam Chomsky, argued that human thought requires language. That is, our thoughts are not just communicated with words, they're actually formed by them.

But F wasn't convinced. She had a hunch that maybe thought and language aren't the same thing at all. So she set out to test it, which means putting people inside this. You up now? That's the sound of me getting prepped for an FMRI at Ev's lab. FMRIs, or functional MRIs, measure how active a specific part of the brain is. So in this task basically you're just gonna see some passages appear on the The screen.

To test if thinking actually does require language, she identified what part of the brain lights up when you hear a story read to you. Then Ev had people solve non language problems, like math equations, for example. And then we ask, do these language regions are they active when you're doing these things? And they're not active. They're basically silent. They're working about as much as when you're looking at a blank screen.

After hundreds of MRIs, Eve reached a surprising conclusion, something that overturned that long standing assumption. In humans, language and thinking are separate. They rely on distinct parts of the brain. And since the brain has a separate language network, it meant scientists could map it, and maybe, someday, even repair it for people with language processing disorders. But this kind of research takes time, a lot of time. Just to get to this initial discovery, it took 15 years.

In part because studying language is hard. Most other scientists can use animals as stand-ins. I've always been jealous of my colleagues who study like vision and motor control because they have this abundance of animal models like mice, you know, some rats. It used to be a mice Much cheaper, much simpler, but you can't use rats to study human language because, well, they don't speak it.

Then something unexpected happened, not in neuroscience, but in technology. When we come back, Ev finds something inside these models that starts to blur a line we thought was pretty clear, the one between how humans think and how machines do. Stay with us. If there was a big red button that would just demolish the internet, I would smash that button with my forehead. From the BBC, this is The Interface, the show that explores how tech is rewiring your week and your world.

This isn't about quarterly earnings or about tech reviews. It's about what technology is actually doing to your work, your politics, your everyday life. And all the bizarre ways people are using the internet. Listen on bbc.com or wherever you get your podcasts. It is called I use the World Wide Web infom. Cybersecurity. Why do things go viral? GPT, the revolutionary new language model developed by OpenAI. It also announced this week Chat GPT can now quote see, hear and speak to you.

I'm interested in how language works and suddenly these um large language models started producing language that was incredibly well formed. So of course me and a lot of people in my group got really excited. Interacting with AI can often sound a lot like a human conversation, in tone, in flow, which raised an intriguing possibility for Ev. If machines can generate conversation like ours, could they be used to study language itself and bypass all the usual complications of studying the brain?

Eve decided to test that. She fed a set of language tasks into a language model, and then she gave the same material to human volunteers. And then you have some metrics that allow you to compare how similar those things are. Say, you know, a few thousand sentences, and then see how these things are represented is similar. So now two systems, side by side. Same input, same task. And what she found took her breath away.

We and a few other groups um have found that when people process sentences, those representations are actually quite similar to what you see inside LLMs. Large language models work by predicting what words should, logically, come next. Eve says our minds do something surprisingly similar. So the human brain is definitely a very predictive kind of a system. Always guessing, always anticipating what comes next.

For brain researchers, this was a massive breakthrough because that bottleneck we started with begins to loosen. All those limitations that used to slow Ev and her colleagues down suddenly started to fall away. Because in a sense she had found a new kind of lab rat, except this one lived inside a computer, which meant she could test ideas that you can't test with real human brains.

It was faster, cheaper, and much more precise. You could pause it, probe it, change one tiny piece, and then watch what happens. Andrea De Varda is a postdoc in Ev's lab. Originally from Italy, he works with her doing that kind of digital dissection. You can also look inside the model and extract activations from individual neurons, which is something that is very hard to do in humans.

Inside these systems are what researchers are calling digital neurons. Not real cells, but close enough that you can study them. And unlike the neurons buzzing around in your brain or mine, these can be measured, isolated, even altered. With LLMs, you can destroy certain components that you with certain uh cognitive capacities in the model. Right.

And see if it changes language. And if it does, maybe that hypothesis is correct. And if it does nothing, maybe you need to rethink your hypothesis. Is that the idea? Yes, that is the idea. So, instead of guessing what the brain is doing, you can test it directly, over and over and over again. Which means scientists can do something they've never really been able to do before. Run controlled experiments on the kinds of processes that usually stay hidden inside our brain.

Evan her team can now start to build a more detailed map of how the brain does what it does.

But language is just the first step. The bigger question is still out there. Can these systems help us understand thinking itself? For a long time Ev was convinced the answer to that question was no. I mean, so in a lot of early models and even a lot of current LLMs, like reasoning tasks, they just clearly don't reason like humans. at least not at first. Then researchers began building something new.

So there is now a class of what's called large reasoning models, which in addition to language are also trained, for example, on a whole bunch of math problems or other kind of reasoning problems. And they're trained These models don't just answer. They show their work. They slow down. They break problems into steps. Andrea showed me how. He rolled his chair up next to me, opened his computer and started typing.

Uh I can ask it a very simple question. For instance, uh how much is twenty-five minus uh four? A green cursor blinked on his screen and then he hit enter. And then the model, as you see here, will generate many, many tokens to solve these questions. So in this case, for instance, for this very simple question, it generated 264 tokens.

Tokens are like the model thinking out loud, one tiny step at a time, line by line by line. In this case, two hundred and sixty-four steps to solve a simple subtraction problem. Then Andrea tried something harder. How much is 24 divided by 7 plus 32 multiplied by 9? This time, there's a long pause, as if the computer is thinking harder. Then the model would generate way more tokens to So it filled the entire screen with Exactly. Lines of code.

Exactly, exactly. And this is the internal thinking of the model. messy, step by step, slower when it's harder. What Eve and her colleagues discovered was striking. Problems humans solve quickly, machines solve quickly too, and harder problems take longer for both. Which raises a bigger possibility. Maybe what Ev was discovering wasn't just about language anymore. Maybe it was about thinking.

And the same way large language models can be used to study language, large reasoning models may be a way to study human thought. A place where you can test ideas about how we reason without waiting years, without needing a human subject at all. Which opens up an entirely new laboratory for neuroscience and new possibilities for brain research that could answer questions like, how humans solve problems, how we learn, what intelligence actually is. And some of those answers might surprise you.

But the implications don't stop there, because the same kinds of models scientists are now using to understand the brain are also being used to understand us. What we want, what we feel, what we buy, how we decide, what we'll do next. It doesn't just observe us, it can anticipate us. For centuries, the brain has been the most mysterious machine we know. Closed off, hard to access, impossible to experiment on directly.

Now, we may have built another one, one not made of cells, but of zeros and ones, a version you can finally examine from the inside. And by studying it, we're not just learning how machines work. We're learning the patterns underpinning our own thinking. What makes us predictable? What makes us human. And maybe the gap between how we think and how machines do is smaller than we imagine. Erica Gaida and Sean Powers field produced this story.

This is Click Here. We'll be back on Tuesday. Have a great weekend. Click Here is a production of Recorded Future News and PRX. Today's show was written and produced by Megan Dietrich, Sean Powers, Erica Gaida, Zach Hirsch, and Casey Georgie. It was edited by Karen Duffin and Sarah Coveto, and fact checked by Darren Ancrum. Original music is by Ben Levingston, with additional music from Blue Dot Sessions.

Our staff writer is Lucas Riley, our illustrator is Megan Goff, and our sound designers and engineers are Jake Cook and Jesse Niswanger. Find us on X or Facebook at Click Here Show. Or leave us a voice message at 6615CH Talk. Sometimes we'll turn those moments into recording, sometimes into a conversation, and sometimes into a future story you'll hear on this show. I'm Dina Temple Reston and thanks for listening.

Support for this program comes from Recorded Future. In cybersecurity, the biggest risk isn't what can be seen, it's what gets missed. Recorded Future analyzes billions of signals to help organizations stay in the Recorded features. Know what matters, act first. If you're looking for a daily guide to cybersecurity news and policy, sign up for the Cyber Daily from recorded future news.

It serves up today's most interesting and important cyber stories from our sister publication The Record and then aggregates all of the big cyber stories you might have missed from news outlets around the world. Just go to the record dot media and click on Cyber Daily to get all you need to know about the world of cybersecurity right in your ears.