📓NOTE: Please forgive the audio quality. I was out on a walk and had been previously interrupted by leaf blowers, hedge trimmers, and skateboarders. At some point you have to ship, especially when the universe has made it clear youre destined not to get ideal audio.

How consistent is generative AI?

That’s a question I’ve been asking since I used Perplexity.ai, a Google replacement that I’ve been meaning to check out for a while but just never quite found the time or motivation to do so.

Seth Godin recently pushed Perplexity in one of his blog posts in which he claimed that he hadn’t performed a Google search in months because he’d been using Perplexity.

So I finally went over to Perplexity.ai and—one, because I’m vain and two, because I think you should search things you know about to test generative AI—I decided to search my name.

The answer it came back with was great and accurate.

It said that I was a writer and blogger at jakelacaze.com and then it gave some of my my views:

Jake LaCaze is a writer and blogger who runs the website jakelacaze.com. Based on the search results, here are some key points about him:

Jake LaCaze values serendipity and embracing uncertainty over relying solely on algorithms and data to curate experiences. He advocates for taking control of one’s online experience rather than being beholden to social media algorithms.

LaCaze is an advocate for Seth Godin’s philosophy of doing work that matters. He appreciates companies like iA Writer that prioritize serving their customers' true needs over pushing unnecessary features.

LaCaze encourages being thoughtful about the digital tools we use daily and bending technology to work for our individual needs, rather than the other way around. He believes processes and workflows should be optimized before adopting new tech solutions.

LaCaze has a critical view of aspects of the tech industry, coining the term “SaaShole” to describe tech bros who prioritize selling solutions over solving customer problems. He is concerned about the motivations and potential negative impacts of tech billionaires.

Overall, the search results portray LaCaze as a writer focused on finding balance and meaning in our relationship with technology, while maintaining a skeptical eye towards the profit motives and potential downsides of the tech industry.’

I didn’t disagree with any of what Perplexity said. I’ve added links to Perplexity’s answers to give ideas of how Perplexity reached its conclusions.

Next, I downloaded the app on my iPhone and I was curious how the same search looked on the iPhone so I searched my name again.

This time it focused on my oil and gas experience.

Two-thirds of the answer was correct but then at the end it said that I have my real estate license and worked for a certain company in Louisiana.

That’s not true.

I’m from Louisiana,but that is another Jake LaCaze that is not hard to find if you just do a quick Google search.

So this brought up an interesting question about consistency and context because it gave me really two different kinds of answers.

The first one leaned on my writing and my views on tech.

The second answer emphasized my oil and gas experience and then went down the avenue of real estate, which is technically related. So I understand why Perplexity confused me and the other Jake LaCaze.

This question about context is really important, because if someone in oil and gas were to search for Jake LaCaze, that person is probably looking for me with my oil and gas experience, but someone else on the internet might just want to know about my tech writing.

It could give different answers depending on who is asking. But if this AI is just generating a new answer every time, what answer is any one person going to get. Does the AI really learn? Would the AI say this person with this Perplexity account is an oil and gas person therefore I should give the oil and gas answer? Would it look at someone else and say: Oh, this person is a tech critic maybe they want to know about Jake’s writing on tech?

These are just interesting questions that I wish we had more answers on.

How exactly does this technology work?

Why did I get two radically different answers?

And also will there ever be a way to reconcile these questions of context and consistency with generative AI?

I can’t help associating Mother’s Day with another holiday: Thanksgiving. That’s because, in 2011, my mother passed away on the Monday after Thanksgiving. Thanksgiving is the last holiday I spent with her.

I owe my mother far more than I can ever properly credit. For 10 years in my early childhood, she raised me as a single mother. When she passed away, my mother had worked at a garment factory in southeast Arkansas for 23 years. Her peak wage was $10 an hour.

As a tired single mother, she prepared me for the future the best way she knew how. She made sure I understood early on that education was my key to getting out of the hometown I couldn’t wait to leave behind. She taught me how to study for tests. She made sure I went to school every day unless I was sick. I didn’t need a prestigious education. (Louisiana public schools have served me just fine.) I just needed an education. And she gave me the stability I needed to focus on being just one tier above mediocre so that I could take on the opportunities waiting for me outside of northeast Louisiana.

I shouldn’t be here, where I am, a humble boy from Middle of Nowhere, Louisiana, making a good life in the middle of the Dallas-Fort Worth Metroplex.

I wouldn’t be where I am today if it weren’t for my mother. She is still the rock upon which I stand.

I was 26 years old when my mother passed away. I wasn’t ready to say goodbye. Even in my mid-20s, I still needed my mommy. And I still do, as I approach middle age.

I often wonder if my mother would be proud of me and where I am. Sometimes, I want nothing more than to hear that sentiment from her. That will never happen. So all I can do is hope.

If you know you owe any semblance of success to your mother–and you know you can never put that fact into proper words–just try. Make the effort. You won’t find the right words. But that’s not the point. The point is in letting her know what you know you can never articulate.

These days, some women lament the idea of being nothing more than just a mother. But there is no such thing as just a mother. A mother brings you into the world. And she is most often the first person to ever love you. We should not discount this simple gift of biology.

So even if your mother is just a mother, let her know you appreciate her. And celebrate the hell out of her while you still can.

Jake LaCaze wants you to say hi to your mother for him.

Would we need therapy if we knew how to slow down and unplug? How to stop distracting ourselves from ourselves?

Convenience has robbed us of these opportunities. As certain tasks have gotten easier, we can now more quickly move to something else. We can more easily switch contexts in the name of productivity.

But is productivity always the goal? Maybe if you’re a widgetmaker. But any widgetmaker who stumbled upon this post has likely clicked on to something else.

What do you do when you’ve been productive enough? Pushing alone can take you only so far.

At some point, you need something else to take you to the next level. A fresh insight. A dash of creativity. Brute force can’t be the only option in your toolbelt.

Insight and creativity aren’t easy to measure, like widgets produced. But insight and creativity are every bit as crucial as pure effort for sustained success.

So what do you need to slow down?

Maybe a comfy chair. Place matters.

What about time?

Sure, time can be hard to find, but it’s more doable if you’ve cut out doomscrolling and those streaming services that are becoming more and more like cable television, the very thing you sought to avoid when you cut the cord.

What if the thing you need to do to improve your life is nothing?

Could you do it?

Could you find the space?

Could you find the time?

If you can’t, fine.

But if you can . . .

Would we need therapy if we knew how to slow down and unplug? How to stop distracting ourselves from ourselves?

Convenience has robbed us of these opportunities. As certain tasks have gotten easier, we can now more quickly move to something else. We can more easily switch contexts in the name of productivity.

But is productivity always the goal? Maybe if you’re a widgetmaker. But any widgetmaker who stumbled upon this post has likely clicked on to something else.

What do you do when you’ve been productive enough? Pushing alone can take you only so far.

At some point, you need something else to take you to the next level. A fresh insight. A dash of creativity. Brute force can’t be the only option in your toolbelt.

Insight and creativity aren’t easy to measure, like widgets produced. But insight and creativity are every bit as crucial as pure effort for sustained success.

So what do you need to slow down?

Maybe a comfy chair. Place matters.

What about time?

Sure, time can be hard to find, but it’s more doable if you’ve cut out doomscrolling and those streaming services that are becoming more and more like cable television, the very thing you sought to avoid when you cut the cord.

What if the thing you need to do to improve your life is nothing?

Could you do it?

Could you find the space?

Could you find the time?

If you can’t, fine.

But if you can . . .

Transcript coming soon

Today’s target for artificial intelligence (AI) seems to be artificial general intelligence (AGI), a technology that is competent in many areas, like humans. AI is most often highly-specialized, focusing on one area with a narrow set of tasks. This sort of AI is best-suited for specialized audiences needing specialized tasks. But with AGI, the prophets of AI can achieve their dream: AI for everyone, everywhere.

Or so the prophecy claims.

We very well may achieve AGI, but I’m skeptical we’ll get there in the next decade (which, compared to the estimates from the prophets of AI, is an eternity). The simple truth is that we still know so little about how the human brain works. Regardless of how some may feel about humans, our brains are complex machines, calculating far more than given credit.

The developers of AGI seem hellbent on replicating and/or replacing humans. But can you replicate or replace what you don’t fully understand? Supplementing and improving upon human intelligence seems a far better goal. This is why I prefer the concept of augmented intelligence over AGI1.

Anyone familiar with SMART goals knows that goals should be attainable—that’s the ‘A’ in ‘SMART’, after all. And I’m not convinced that replicating or replacing human thought and processing will be attainable in the near future.

If Gary Marcus is right—if the hype seems to be dying and the return on investment just isn’t there2—then it feels as if AGI will be attainable much, much later than the prophets of AI would have us believe.

AI Should Augment Human Intelligence, Not Replace It from Harvard Business Review ↩︎

The ROI on GenAI might not be so great, after all by Gary Marcus ↩︎

Some people want to be left alone to do their own work and go home and call it a day. There’s nothing wrong with that—I support your right to curate your own experience. But by working in such fashion, there’s only so much you can do.

There are only so many hours in a day, you have only so much energy, there are only so many tasks you can give your attention to.

At some point, you as an individual hit a wall. You’ve largely gotten as good as you’re going to get. Any improvements will likely be incremental and lower in impact than previous improvements.

If you find yourself in this position, maybe it’s time to start looking beyond yourself. Maybe it’s time to see if you can help others within your team—however you define that term—improve in the areas that hold them back.

Maybe it’s time to mentor. To scale your impact and elevate those around you.

Maybe it’s time to lead.

I could try to tell you what exactly Douglas Rushkoff’s Survival of the Richest: Escape Fantasies of the Tech Billionaires 1 is about via a traditional book review, or I could hope that an inspired rant might give you a better idea. If you haven’t already figured it out, I’m choosing the latter route.

The tech billionaires have one simple goal: to shelter themselves from the world they’ve shaped with their outsized wealth, power, and influence. Undoing all they’ve done in the name of making true positive change via small incremental improvements that risk going unrecognised is beyond them. Simply having the option to escape this world via one avenue or another shows that the tech billionaires already live in a reality far different from the one most of us inhabit.

Rushkoff starts by describing the struggles of those tech billionaires outfitting their doomsday bunkers for the coming apocalypse2. A lot of thought goes into such preparation. Location, supplies, air filtration. The tech billionaires are also looking into how to motivate their security to protect them when the markets collapse and currency is worthless.

Others hope to one day leave the earth behind. They plan to colonize Mars and start over new, where they’ll stand to gain even more as the early adopters of a fresh society.

But what about those tech billionaires who can’t escape in these ways? What if they have no choice but to stay on this boring earth, and what if everything doesn’t go to absolute hell and they can’t justify running away to their bunkers in Hawaii or New Zealand?

That’s where digital escapes like the Metaverse come into play. Who needs Mars or a doomsday bunker when they can build a digital world to replace the physical. You can always buy digital real estate and rent it out to supplement any losses realised from your real estate in the unplugged world3. Some might call this strategy ‘diversification.’

Can you be tied to the world around you if your mind is set on escaping? Are you invested in the slightest? If the answer is no, then why do we let these select few build a world we’ll be stuck with when they flee the first chance they get? If you already have one foot out the door because you’re convinced that to stay is hopeless, then at what point is reality a foreign concept? And if you’re so sure that a certain outcome is inevitable, when does everything begin to look like a prophecy? And when do you decide that resistance is futile? You might as well get what you can while you can. Just make sure you get enough to help you get away at a later date.

Perhaps we can’t blame the tech billionaires for looking forward to their own big exit, when their investors expect their own such exit, usually in the form of an IPO or flipping the company at some multiple of their original investment.

Many in tech have long adopted Mark Zuckerberg’s mantra to ‘Move fast and break things.’4 But tech’s secondary mantra appears inspired by Matthew Good5:

We’ll stick to the plan:

The fall of man

The tech billionaires aren’t worried though, because as man falls, they will rise, whether to Mars, the Metaverse, or to the safety of their underground bunkers.

No big deal though. I’m sure they’ll wave bye and give a heartfelt thanks for all we’ve done to enable them to get the hell out of Dodge as they leave us to our fates6.

‘Why is Mark Zuckerberg building a private apocalypse bunker in Hawaii?’ on The Guardian ↩︎

‘Inside the lucrative business of a metaverse landlord, where monthly rent can hit $60,000 per property’ on Fast Company ↩︎

‘The problem with “Move fast and break things”—Tech needs a better guiding principle’ on jakelacaze.com ↩︎

‘The Fall of Man’ by Matthew Good Band on YouTube ↩︎

‘Jeff Bezos thanks Amazon customers and employees who “paid for all this”’ on CNN ↩︎

Just taking a moment to reflect where we are in our energy needs in the middle of 2023, with the help of micro.blog’s Wavelength app

So as I’m gearing up to get back into oil and gas/energy, I’ve been hearing a couple of themes repeated over the last few days.

One is that oil production will peak in 2030.

A lot of logic is that the Permian will have peaked and we will have drilled most of our prime locations. This makes sense.

You always drill your prime locations first to get that return immediately and impress your shareholders. Also, you’re gonna get less from wells right now. There’s gonna be higher degradation, less initial production right off the bat, and we’re drilling less just in general.

So if that all remains the same, yeah, it checks out.

Another thing I’ve been hearing repeated is that by 2030 at least 35% of all new vehicles will be electric. Maybe higher than 50%.

This is at a time when we’re pushing for renewable energy, notably solar, and all these different types of energy will be fighting for the same precious metals, which we will need to increase four, five times, six times as much, depending on what exactly you’re talking about.

So what are the environmental concerns of that? Mining those minerals. Not just environmental, also political, and how exactly are we going to get those minerals so fast and make everything we need out of them?

Energy is going to be a big problem in coming years, and it’s one that we need to get right.

Going back to the Stone Ages is not the answer. That doesn’t really benefit anyone. And trying to keep developing nations from using energy to grow into the new world is also not an option. It’s also very hypocritical of us, already developed, to expect them to stay stagnant.

While people’s perception of nuclear is changing and becoming more positive, the unfortunate fact is that nuclear takes a long time to get online. So even if we started today, we probably would not have enough nuclear to really make a difference by the coming of the next decade.

So what we have to accept is that every energy solution comes with trade-offs. There is no easy solution, so we have to be mindful about what trade-offs we’re willing to make and to be honest about the consequences.

Again, there just is no easy way where everyone wins 100%, and we have to find that right balance because, again, this is too important not to get right.

I dropped $10 on the micro.blog Premium subscription. So I might as well see if I can get a podcast/microcast going.

Mic check, mic check.

This is Jake LaCaze.

Hard to believe it was only early last year that I was announcing to y’all that I was leaving oil and gas and trying my hand at marketing.

It was fun for a while, until it wasn’t.

Now I’m headed back into oil and gas.

Well, I’m really kind of headed back into energy, though oil and gas will be my immediate job responsibilities.

It’s an exciting time to be back in the energy space: Oil and gas is embracing other forms of energy. They’re no longer standing on their own.

It’s kind of like we’re all in this together. We know what’s ahead. We know what the stakes are.

We’ve got to figure it out.

Getting our energy portfolio right won’t be easy.

There are challenges that lie ahead, but with challenges come opportunities.

Necessity is the mother of invention. We’re at a time where we need innovation wherever we can find it.

That’s the journey I see myself on in the coming future, looking at the whole of energy and trying to figure it out and see what fits where and just exactly can we fix the problems we have ahead in a pragmatic way that benefits all involved.

So if you’re interested, come along.

Let’s figure this out together.