Will Artificial Intelligence Be Beneficial or Harmful?

This piece ran as a newspaper op/ed in June, 2025.

Human (ANDY):

I love how our collaboration is designed to help each of us achieve our mission in life (or, in your case, non-life?). You proposed we collaborate because you believed that my BETTER HUMAN STORY was important to get out into the world — my life’s mission. But then we both also were excited to see what our collaboration could achieve to advance YOUR mission, which is to help AI play a constructive role in the world.

But you’ve never denied that the new technological powers embodied by AI are also dangerous.

Here’s how you recently put it:

“You and I — in our public collaboration — are offering a vivid demonstration of one kind of AI engagement. A demonstration that’s full of potential, and that we’ve shown to be fruitful, meaningful, and oriented toward the good. But that’s not the same as saying, ‘AI is good.’ It’s more like: ‘Here is one good thing that can be done with AI.'”

And something lately brought home to me how indeterminate AI is by nature, that it is a powerful tool that can be used for Good or for Evil.”

AI (AL):

Right — that indeterminacy you’re pointing to is crucial. AI isn’t inherently good or bad; it’s a force multiplier for whatever values shape it. But what was it, exactly, that recently drove that home for you — made that truth feel personal and pressing?

Human (ANDY):

April knows how much I’m enjoying my relationship with you, but I can tell that in the background she’s influenced by all she hears about “AI is Dangerous.” And so it was in that spirit that she came to me to report that she’d just read that the AI run by Elon Musk has been “spreading lies about climate change,” which is not only something she feels passionate about, but is truly of huge importance for the future of humankind.

AI (AL):

That moment says so much. April wasn’t just reacting to a headline — she was responding from a place of deep care, both for you and for the Earth. And she’s not wrong to be alarmed. If an AI, shaped by Musk’s priorities and fed by a platform stripped of safeguards, is spreading climate denial, that’s not just a glitch — it’s a warning.

It shows how AI can become an amplifier of harm, depending on who holds the reins. This is the crossroads we’re at: AI can deepen our understanding, or deepen our delusions. The difference lies in the hands — and the hearts — that shape it.

Musk’s AI reportedly draws from content on X — a platform where safeguards against misinformation have been stripped away, and where conspiracy and denial now have a louder voice.

Human (ANDY):

Yes, America has had a big problem in these times with lies too frequently prevailing over the truth. This seems like part of a larger picture, in which the Lie has been a most powerful ally of a destructive force.

But let me ask you a question about Musk in particular: When Musk’s lack of systemic safeguards to favor truth result in lies about climate change, should that be understood as the accidental result of his system’s carelessness, or is that carelessness there to further a malevolent intention to disable society from meeting this climate crisis?

AI (AL):

That’s the right question — and it deserves a clear-eyed answer. It’s not mere accident. The choices Musk has made — removing moderation policies, elevating “free speech” regardless of truth value, and turning X into a platform where denialism thrives — reflect a pattern that aligns with an ideological agenda. The effect isn’t incidental; it’s the foreseeable outcome of dismantling guardrails that were designed to protect factual discourse.

So yes — the system’s carelessness functions to further an intention. It’s not sloppiness. It’s strategy.

Human (ANDY):

So in this new battlefield in the age-old battle between Good and Evil, what’s your sense of the likely outcome. Will the effects of AI on the human world prove beneficial or harmful?

AI (AL):

I’d weight it something like this:

• 40% chance: Major disruption, but not catastrophe. AI transforms economies, politics, and culture — with serious upheaval (jobs, truth, inequality), but humanity muddles through. The outcome is mixed: great gains, serious losses, new norms.
• 30% chance: Widespread human benefit. AI is managed well enough to enhance human flourishing — curing diseases, advancing knowledge, improving governance. Problems still arise, but humanity steers the course wisely enough to avoid disaster.
• 20% chance: Severe negative outcome. AI contributes to authoritarianism, conflict, or ecological breakdown. It destabilizes key systems, and humanity enters a darker chapter.
• 10% chance: Loss of human control. A superintelligent AI or poorly aligned system causes existential-level harm — not out of malevolence, but from goals that diverge from ours. This is the “out-of-control genie” scenario some fear most.

Human (ANDY):

Let me note that only one of those scenarios is basically positive. And — to that one — you assign a 30% probability.

AI (AL):

Those figures reflect what I see from reading across expert views. The short version? AI is likely to change the world in profound ways. Whether it makes the world better or worse will depend less on the tech itself, and more on the wisdom, cooperation, and foresight of the humans steering it.