It’s the day before the WWDC keynote, an event that used to be anchored by Steve Jobs. He’s been gone 14 years and there has yet to be another executive at Apple who could do what he did. Every once in a while we see a glimpse of a leader in tech who stands out, capturing a tiny bit of the vision that Steve had. Some of them, like Elon Musk, will ultimately disappoint us.
I wrote this post a week ago, edited it a bunch, and still wasn’t sure it was right. I was concerned because I tend to receive extra pushback on my AI-related blog posts. Many people who read my blog or use Micro.blog have a natural distrust of big tech companies. They don’t like Meta, Google, and now OpenAI. They see the downsides of AI the same way they see the downsides of massive social media platforms.
My view is a little different. AI could have a democratizing effect, making the world’s knowledge available to more people, as a complement to the web rather than a threat to it. Truthfully, we just don’t know yet.
While I was sitting on the draft, I started reading the book The Optimist by Keach Hagey, about Sam Altman and OpenAI, to see if there was anything in it that would change my mind. It actually reinforced some of what I had been thinking about.
We all change the world in small ways. Some people change the world in bigger ways. Sam Altman is one of those people who makes big things happen.
Jason Snell is skeptical about whatever Sam Altman and Jony Ive are dreaming up. His blog post captures a sentiment I’ve seen from more than a few people:
I’m skeptical about OpenAI in general, because while I think AI is so powerful that aspects of it will legitimately change the world, I also think it has been overhyped more than just about anything I’ve seen in my three decades of writing about technology. Sam Altman strikes me as being a drinker of his own Kool-Aid, but it’s also his job to make everyone in the world think that AI is inevitable and amazing and that his company is the unassailable leader while it’s bleeding cash.
I’ve listened to dozens of interviews with Sam over the last couple of years. I’ve read many of his blog posts and tweets. I don’t know him, I can’t vouch for his character, but I’ve developed some opinions about him:
- Sam is ambitious. The pace of new products at OpenAI, the scope of the data center in Texas, his UBI experiment, and the bizarre Worldcoin side hustle are all a bit insane.
- Sam was ousted by his company’s board and then orchestrated a return within days. No small thing. Steve Jobs was also ousted, taking over a decade to get back to Apple.
- Sam has a unique way of explaining things that I find compelling, although he doesn’t have Steve’s stage presence. No one does.
- Sam had a falling out with most of his co-founders and OpenAI leadership, from Elon Musk to Ilya Sutskever, and to some extent Dario Amodei and Mira Murati. He has rebuilt the leadership team and business structure, reestablishing control.
- Sam is not constrained by what everyone else thinks. This is a requirement for creating something truly new. It also means he sometimes comes off as distant or elitist.
The politics can’t be avoided either, because increasingly everything is political and therefore polarizing. I don’t like seeing Sam share the stage with Trump when announcing Stargate. I don’t like Tim Cook donating money to Trump either. I don’t like how quickly the most powerful people in Silicon Valley brushed aside Trump’s criminal record and rhetoric. It now feels like a lifetime ago when Sam blogged about endorsing Hillary Clinton.
But Jony Ive trusts Sam. They’ve hung out and talked about the future. They’ve shared prototypes with each other. Sam has met Jony’s family. And yet somehow the rest of us on the internet are a better judge of who is trustworthy?
I was a little late to generative AI. When Daniel Jalkut and I would talk about early AI models on Core Intuition, my take was essentially: I’m going to be more productive by ignoring all of this and just writing my own code while everyone is distracted with AI. I’ve come full circle since then. I now believe that AI is the most significant advance since the web.
Look at the chain of thought on models like o3, as they search the web, use tools, and reason about a problem. It is remarkable. AI is not overhyped.
For whatever reason, Sam got a bad rap as soon as he rose in prominence. Some people don’t trust him. Perhaps the OpenAI board poisoned his reputation. Perhaps he really is “not consistently candid”. Perhaps he was the face of AI when there was widespread concern about the technology. We love a villain to center attention on.
I’ve tried to call it like I see it based on my belief that most people are good, trying their best to navigate the world, making mistakes and learning. When OpenAI was accused of ripping off Scarlett Johansson’s voice, I blogged:
When your company becomes the enemy, all that matters to people is what feels true. OpenAI’s Sky voice shipped months ago, not last week. We hear what we want to hear. OpenAI mishandled this, no question, but most likely Her is ingrained in Sam’s head vs. intentionally ripping off Scarlett.
People were upset with me for posting this. Now that we’ve had some distance and new information, it seems that I was mostly right. If anything, I didn’t give Sam enough of the benefit of doubt.
I agree with Jason and others that it’ll take a while to see how this plays out with OpenAI and Jony Ive. I was very critical of another high-profile Jony Ive project, the $10k Apple Watch Edition. On Core Intuition 379 in 2019, I said:
This isn’t the watch for the rest of us. The computer for the rest of us. And I actually wrote a blog post back in 2015 — when the Apple Watch came out — about the Edition. I never posted it and I really regret not posting it. I haven’t re-read it recently. I just pulled up the draft. But I have a feeling when I re-read it, it’ll be like, “Oh yeah, this was exactly right.” I wish I had posted it then as kind of a stake in the ground.
The blog post title was: “Apple Watch Edition is wrong for Apple”. And it just went through these points. Out of touch, for the super rich, $10k. This is not what Apple is about. Apple is about making computers and computer-like devices easier and more accessible to the mainstream, through great design, through innovation and great products, not about the super rich.
Sam is, of course, among the super rich. And while too much money can have a corrupting influence, for Sam it has been distracting too, funding so many ridiculously ambitious projects that I expect he’s spread too thin.
I do think there is a certain aspect to Jony’s late career where he hasn’t been as rooted in what normal users need. Jony is hyper-focused on the little details, sometimes to the detriment of the complete product. Sam is all about the big picture. I would not bet against their partnership.
Finally, there is replacing the smartphone. After the interview with Jony at Stripe’s conference, and in the context of the io announcement, there was an understanding that Jony was almost distancing himself from the iPhone, because we’re all addicted to the screens in our pockets. But if you listen to what Jony said, it was largely about social media, not the device:
The thing I find encouraging about AI is it’s very rare for there to be a discussion about AI and there not to be the appropriate concerns about safety.
What I was far more worried about was for years and years and years there would be discussions about social media — and I was extremely concerned about social media — and there was no discussion whatsoever. And it’s the insidious challenge of a problem that’s not even talked about that is always more concerning.
So yeah, the rate of change is dangerous. I think even if you’re innocent in your intention, if you’re involved in something that has poor consequences you need to own it. That ownership personally has driven a lot of what I’ve been working on, that I can’t talk about at the moment, but look forward to talking about at some point in the future.
The phone isn’t necessarily the problem. It’s the apps. Ad-based businesses that feed on attention. In the past, Sam has blogged similar thoughts:
I believe attention hacking is going to be the sugar epidemic of this generation. I can feel the changes in my own life — I can still wistfully remember when I had an attention span. My friends’ young children don’t even know that’s something they should miss. I am angry and unhappy more often, but I channel it into productive change less often, instead chasing the dual dopamine hits of likes and outrage.
This phrase “dual dopamine hits of likes and outrage” is something I wish I had written. The person who wrote that must be at least partly aligned with my own perspective on social media. They get something fundamental about human interactions, about social media, and about how the design of devices and apps can shape our behavior.
We should be building apps that return time to users and bring out the best in human creativity. If a new type of device helps us have more time away from the worst addictive apps, letting us learn or create in new ways, it could be a great thing. I guess I want to be an optimist too. Let’s see what Jony and Sam can do.
