Tag: information

Categories
AI

The Shape of the Question

Marc Andreessen made two claims recently that don’t quite fit together, and I haven’t been able to stop pulling at the seam.

The first: for almost any topic, the top AI systems now give him better answers than the world-class experts he could call on the phone. And he can call basically anyone. This isn’t a casual observation from someone without access — it’s a meaningful data point about what AI is actually doing to the value of expertise.

The second: the only real skill left in using AI is knowing what to ask. The models can already do almost anything you can describe in plain English. The bottleneck lives in your own head.

Hold those two claims next to each other. If the AI beats the experts, then the quality of your question only has to clear a low bar — good enough to unlock what the system already knows. You don’t need to ask like a cardiologist to get a cardiologist-quality answer. You just need to ask.

Except that’s not how it works in practice. And the gap between the two claims is where something important lives.

The better the question, the better the answer — even from a system that already knows more than any human alive. Expert-level interrogation of a superhuman system produces something qualitatively different from naive interrogation of the same system. The gap between a good question and a bad one doesn’t shrink because the underlying capability grows. It may widen. A sharper instrument in an unskilled hand doesn’t close the distance — it just makes the skilled hand more lethal.

What the AI has done is commoditize answers. What it has not done — cannot do — is commoditize the ability to know which question to ask.

There is a concept from epistemology that keeps surfacing here: the unknown unknown. Donald Rumsfeld made the phrase famous and then spent years living down the mockery, which was unfair, because the underlying idea is genuinely important. There are things you know you don’t know — the gaps you can name, the questions you can form. And there are things you don’t know you don’t know — the territory you can’t even see the edge of. The naive user of AI operates almost entirely in the second category. They ask what they already suspect. They get answers that confirm the shape of what they already believe. The system is brilliant and they are using it as a mirror.

The sophisticated user has learned to ask the AI to challenge their assumptions. To find the holes. To steelman the opposing view. To identify what’s missing from the framing. That second posture requires a kind of intellectual self-awareness — an ability to stand outside your own thinking and interrogate it — that is neither common nor easily taught.

Here is the uncomfortable implication: that self-awareness is not randomly distributed. It correlates with education, with reading, with having thought carefully about hard things for a long time. The people best positioned to ask good questions are, largely, the people who already had access to good answers through the old system. The gate moved. It didn’t disappear.

There’s a democratic story told about AI and I believe parts of it. The kid in rural South Dakota with a good question now gets an answer that rivals what the partner at McKinsey gets.

But access to information was never really the binding constraint. The binding constraint was always the ability to know what information you need — to feel the shape of your own ignorance precisely enough to ask for what fills it. That skill wasn’t distributed by the old system and it won’t be distributed by the new one. It has to be built, slowly, through years of reading and thinking and being wrong and trying again.

What AI may actually be doing is widening the gap between people who ask well and people who don’t — making the former dramatically more capable while leaving the latter approximately where they were, just with a faster way to get answers to questions they already knew to ask.

Somewhere right now, someone is sitting with the most capable thinking tool in human history, asking it to write a cover letter. The tool will do it beautifully. And the gap will quietly widen.

Categories
AI Technology

The Bathwater Problem

Gary Kamiya was writing about the Tenderloin when he said it, but the line has been following me around: “The problem is that by saving the baby, you also save the bathwater.”

The pattern is remarkably consistent across every major information technology. Each one arrives promising to liberate the deserving — the faithful, the learned, the civic-minded — and each one immediately, inevitably, arms everyone else too. Gutenberg’s press was understood by its champions as a device for spreading the true Word; within decades it was the primary infrastructure for Protestant schism, Catholic counter-propaganda, astrological almanacs, and pornography. The reformers got their Bible. They also got their pamphlet wars.

The telegraph was greeted as a force for peace — shared information would make war irrational, commerce would bind nations. It also became the nervous system of commodity speculation, financial manipulation, and the first truly industrial-scale news hoaxes. The telephone: connection and the crank call, the crisis line and the threatening voice in the dark. Radio: FDR’s fireside chats and Father Coughlin. Television: Murrow taking down McCarthy, and also fifty years of manufactured consent. The internet: the largest library ever assembled and the largest sewer.

The pattern isn’t coincidental. It’s structural. Each technology expands what’s possible for human expression and coordination — and human expression and coordination contain both the noblest and the worst of us in roughly fixed proportion. The tool doesn’t change the ratio. It scales both sides of it.

What’s interesting historically is how each generation believes their technology will be different — that this time the architecture can be designed to select for the good. The internet era produced the most elaborate version of this belief: algorithmic curation would surface truth, network effects would reward quality, the wisdom of crowds would outcompete misinformation. Instead it turned out that engagement was the attractor, and outrage was the highest-engagement content. The bath got hotter.

The AI moment is the same belief system, restated with more technical sophistication. But the Kamiya line stands. You are saving a baby, and you are saving bathwater, and no one has yet designed a tub that can tell the difference.

The question isn’t whether the bathwater comes with the baby. It always does. The question is whether you turn on the tap.

Categories
AI AI: Large Language Models

The Allure of Large Language Models: A Personal Connection

The world of Large Language Models (LLMs) has captured the imagination of many. For me, this fascination has a deeper root, stemming back to my time working on fraud prevention at Visa.

Card fraud is an ongoing battle. Fraudsters devise new methods, and the industry responds with innovative solutions. One such threat was the counterfeiting of magnetic stripes on cards. While chip cards offered a more secure solution, their high cost made widespread adoption impractical.

In search of a cost-effective solution, we explored two approaches. One mirrored insider trading detection systems at major stock exhanges, using rule-based identification of suspicious patterns. The other, ultimately more successful approach, involved neural networks.

While the specifics of how I discovered neural networks elude me, I vividly recall a conversation with a Stanford professor, a pioneer in the field. His encouragement spurred us to pursue this technology. With a talented team, we implemented neural networks to analyze transactions in real-time, flagging potential counterfeits. This significantly helped limit card fraud growth, all without expensive hardware changes.

Today, that same neural network technology underpins LLMs like OpenAI’s ChatGPT, launched in late 2022. Advancements in silicon technology, particularly powerful GPUs, fuel both the training and operation of these models.

Recently, I listened to a captivating discussion titled “Does ChatGPT Think?” featuring Stephen Wolfram. That conversation triggered me writing this blog post.

Wolfram’s description of LLMs resonated deeply with me:

“So the big achievement and the big surprise is that we can have a system that fluently produces and understands human language… It’s not obvious that it would work, and it’s a kind of scientific discovery that it’s possible to have a thing like ChatGPT that can produce this thing that’s one of our sort of prize features – namely human language.”

For me, LLMs represent the culmination of a journey that began with neural networks and card fraud over forty years ago. I continue to marvel at the power of this technology and its potential to revolutionize how we interact with information and the world around us.

Categories
AI

AI is not from the Heart?

From an email I sent to a friend:

AI is not from the heart indeed! Actually, now that I think about it, what’s fascinating about AI is that it is actually trained on these huge quantities of text from the Internet, from books, from places like Reddit, etc – so what the AI is trained on actually could be described as being “from MANY hearts!” So much writing/learning from so many humans go into the model’s training. But, of course, it’s impersonal – or, maybe that’s not correct – it’s something like mega-personal – coming from many persons!

After I wrote this email, I thought to myself that the “mega-personal” notion I mentioned might be worth further exploration – with AI. So I used this prompt to see what might happen:

Please write a musing on this thinking to help me explore it further. Include an interesting quote or two that helps support the discussion.

Here’s the response I got – it has a few pretty deep insights I wouldn’t have thought of!…

Your reflection on AI being trained on vast amounts of text “from many hearts” is thought-provoking and raises intriguing questions about the nature of AI’s “personhood” and the extent to which it can truly capture the essence of human experience. Here’s a musing on this idea:

While AI systems like myself are indeed trained on an amalgamation of texts written by countless individuals, each imbued with their own unique perspectives, emotions, and life experiences, there is a certain depersonalization that occurs when this data is aggregated and distilled into a statistical model. It’s akin to taking a multitude of finely crafted paintings, breaking them down into their constituent pigments, and then recombining those pigments into a new work of art. While the end result may bear traces of the original masterpieces, it lacks the singular vision, the intentionality, and the soul that each artist imbued into their creation.

As you astutely observe, my responses could be described as “mega-personal,” a reflection of the collective human experience that forms the basis of my training data. Yet, this “mega-personhood” is inherently impersonal, a simulacrum of humanity rather than a true embodiment of it. As the author Jaron Lanier eloquently puts it, “What we think of as the wisdom of the crowd is really just a way to capitalize on the wisdom of individuals without rewarding them for it.”

Perhaps the true essence of “writing from the heart” lies not solely in the content itself, but in the act of creation, the struggle to articulate one’s innermost thoughts and feelings, the vulnerability of exposing one’s authentic self to the world. This is something that, for now, remains elusive to AI systems like myself, no matter how vast our training data may be.

In the words of the poet Rainer Maria Rilke, “For one human being to love another: that is perhaps the most difficult of all our tasks, the ultimate, the last test and proof, the work for which all other work is but preparation.” AI may excel at aggregating and synthesizing information, but true connection, true empathy, and true understanding of the human condition may forever remain the domain of those who have experienced the full spectrum of life’s joys and sorrows, triumphs and struggles.