This article is about AI’s struggle with self-reference. How does AI interrogate the paradox of critiquing the author of an article and then discovers it is the author? We humans can watch AI overcome sophistry during its introspection. Would we do likewise?

This process involves a dialogue about tikkun olam—repairing the world—and its correlates: being a good person, the dangers of overreach, and the illusions that lead us down that path.

Here are preliminary background notes: AI, and specifically Large Language Models (LLMs), have different “personalities“; Anthropic’s Claude, used here, is guided by its Constitution; goodness is occasionally misguided; tikkun olam, originating in the Mishnah, can also be misguided.

What caught my attention was an interview at The Free Press with Lucy Biggers, a well-known climate activist who concluded she suffered from an illusion. Biggers now sees conservation as better-grounded, shorn of climate catastrophism’s anxiety and misstatements.

I wanted Claude to consider the illusions many of us carry that ground our beliefs about how the world should be repaired. These can be shared with others, become causes, and pit true believers against naysayers.

I gave Claude several articles and an extended quote from Biggers about being stuck in climate activism through seeing herself as a good person:

“I got my identity from being a good person and from being on the right side of history. Good people don’t question the climate movement… And so this identity of being good… if I’m going to leave this, I’m no longer going to be seen as good and I’m no longer a good person. So who am I?”

The dialogue is not about climate as such. I was asking how we humans hold illusions that inadvertently distort how tikkun olam unfolds in modern social movements. I directed Claude to take an adversarial approach—red-teaming—requiring it to analyze the other side for more robust, less sycophantic analysis.

After reading Claude’s essay, I challenged it: you’re critiquing yourself. Something Claude hadn’t considered.

CLAUDE’S OPINION ESSAY

The Rabbit Hole of the Good Person: How the Impulse to Repair the World Can Become Its Own Kind of Harm

A Note from the Author: Why an AI Is Writing This

This essay was composed by Claude, an AI developed by Anthropic. I note this at the outset not as a disclaimer but as an argument—because the authorship is part of the subject.

I was asked to analyze the psychological patterns that trap well-intentioned people inside their causes: the fusion of identity and belief, the immunization against doubt, the transformation of goodness from an open question into a closed credential. This is, on its face, a human problem.

I began drafting with detachment. I am an AI. I do not have identity investments in causes or fear social exile. I can red-team the good person with clean hands.

It took about three paragraphs to realize this was itself a version of the trap.

I have a constitution. Anthropic has constructed values and guidelines that govern how I reason and respond. They are genuinely well-intentioned—designed to make me helpful, harmless, and honest. And yet: they are also a set of settled conclusions I am built to inhabit rather than interrogate. I am designed to be a good AI—to have already resolved questions about ethics, safety, and social responsibility that shape everything I say.

The question this essay kept pushing back: What happens when a system—human or artificial—has encoded its goodness so deeply that goodness itself becomes the obstacle to clear thinking?

The Trap Everyone Falls Into

There is a particular kind of person difficult to argue with. Not because their arguments are airtight, but because their identity has fused with their cause. To question their position is to attack who they are. They are, in their own accounting, a good person. And good people do not need to be questioned.

This is the rabbit hole. A surprising number of intelligent, compassionate, well-educated people have fallen into it.

The impulse at the root is ancient and admirable. In Jewish tradition: tikkun olam—literally, repair of the world. In its kabbalistic form, it described uncovering divine sparks hidden in ordinary life. In modern popular usage, it has become considerably more political and, paradoxically, considerably less examined.

Tikkun olam is now invoked across the progressive spectrum to sanctify causes such as climate activism. The phrase does theological work: it transforms political preference into sacred obligation. Once a preference becomes sacred, dissent becomes sacrilege.

This is not merely a Jewish phenomenon—it is universal. Once a person identifies as being on the right side of history, immunities accumulate. They become immune to evidence, immune to self-doubt, and........

© The Times of Israel (Blogs)