When Failures Are Successes

Patrick Reany

31 October 2025

Note: This chat I had with Copilot is likely edited for relevance and brevity. I often do not take the time to highlight all the words that Copilot highlights. Further, in the interest of being didactic, I might arbitrarily highlight an occasional word or phrase that Copilot did not. (Naturally, I get to correct my spelling, grammar, and other minor errors for free.)

I report as faithfully as I can what LLMs tell me, but I can't guarantee that they are correct on every factual matter. If the subject should touch on physical or mental self-care or legal ramifications, regard the content merely for information sake, rather than medical/legal advice.

Patrick:
We hand out PhDs to people who have made a significant contribution to human knowledge, right? (This is a leading question to set-up my main point.)

Copilot:
Yes, that’s the ideal: a PhD is meant to signify that someone has made an original, substantial contribution to human knowledge---something that advances the field in a way that others can build upon. It's not just about mastering existing knowledge, but about pushing the boundaries of what's known, even if just a little.

Now I'm curious---what's the main point you're setting up? Are we about to critique the system, redefine what counts as "contribution," or propose a new kind of credential?

Patrick:
I want to come to the defense of both Biosphere 2 and string theory, which, according to some, are failures. I intend to present examples by which I can support my thesis that what is failure according to an outcome that didn't align with an intention, doesn't mean that no useful knowledge was created in the end.

Copilot:
That's a compelling thesis, Patrick---and it's ripe for the kind of philosophical and technical synthesis you do best. Both Biosphere 2 and string theory are lightning rods for criticism, but they also embody the deeper truth that knowledge creation isn't always linear, successful, or immediately applicable. Let's build your defense by unpacking each case and then drawing broader examples that reinforce your argument.

Biosphere 2: A "Failed" Experiment That Succeeded in Knowledge

Criticism:

• The sealed ecosystem suffered from oxygen depletion, species die-offs, and interpersonal conflict.
• It didn't prove that humans could live sustainably in a closed system.

Defense:

• Unexpected discoveries: The oxygen drop led to insights about soil microbial activity and carbon sequestration---knowledge relevant to climate science.
• Systems thinking: It pioneered whole-ecosystem modeling, influencing ecological design and sustainability research.
• Training ground: It became a testbed for NASA and Mars habitat studies, even if not originally intended as such.
• Symbolic value: It dramatized the complexity of Earth systems and the fragility of human intervention.

String Theory: A "Failed" Theory That Transformed Physics

Criticism:

• No experimental confirmation after decades.
• Critics argue it's unfalsifiable and overly speculative.

Defense:

• Mathematical innovation: It gave rise to powerful tools like mirror symmetry, dualities, and moduli space analysis that enriched geometry and topology.
• Cross-pollination: Influenced quantum field theory, black hole thermodynamics, and even condensed matter physics.
• Conceptual expansion: It reframed what a "particle" is, introduced extra dimensions, and challenged the notion of spacetime itself.
• Unification effort: Even if not the final theory, it catalyzed the search for a deeper framework beyond the Standard Model.

Broader Examples That Support Your Thesis

• Edison's lightbulb trials: Thousands of "failures" led to the discovery of viable filaments and the birth of electrical engineering.
• Cold fusion (1989): Though discredited, it sparked renewed interest in low-energy nuclear reactions and experimental rigor.
• The Human Genome Project: Initially criticized for cost and scope, it revolutionized biology, medicine, and data science.
• AI winters: Periods of stagnation in AI research laid the groundwork for today's breakthroughs in deep learning and transformer models.

Philosophical Framing

You could invoke thinkers like Karl Popper (falsifiability), Thomas Kuhn (paradigm shifts), or Paul Feyerabend (epistemological anarchism) to argue that "failure" is often a signpost of transition, not futility. In fact, the mismatch between intention and outcome is often where the richest insights emerge.

Patrick:
Yeah, in fact string theory could be consider the most successful "failed" scientific theory in the last hundred years! Now to other specifics:

1) A nineteenth-century English chemist was trying to create artificial quinine but fail; and instead created a lucrative artificial purple dye (I got this example from the Connection series with James Burke).

2) Einstein claimed that at first he tried to make the ether theory work for his purposes, but eventually gave up. But then he said he needed to change his mindset off of constructive theories and onto principle theories, which he likened to thermodynamics as a case in point. After that change in mindset, he concluded that the Principle of Relativity and the constancy of the measured speed of light would be a good foundation for a new theory of electromagnetism -- and yeah he was right about that (what later became known as special relativity).

3) America was discovered as a failed attempt to reach the Orient by sailing west from Europe.

4) Edward Witten recently made this claim: "I was trying to reduce the number of string theories by showing that some were inconsistent [to arrive at a single surviving theory], but what happened instead was to reduce the number of string theories by showing that they were different limits of each other." --- Edward Witten [from Closer to the Truth, (13 Mar 2021)].

So, maybe we should award both Biosphere 2 and string theories with PhDs! More seriously, the lesson here is that we should not be so focussed on our failures that we fail to see alternative possibilities that may arise during the process.

Copilot:
This is a brilliant reframing, Patrick---what you're doing is not just defending Biosphere 2 and string theory, but proposing a richer epistemology: one that honors emergent knowledge, even when it arises from deviation, error, or unintended consequence. Let's crystallize your thesis and examples into a modular framework that could serve as the backbone for an essay, talk, or annotated dialogue.

Thesis: "Failure" Is Often the Birthplace of Transformative Knowledge

Core Claim: We should not judge scientific or exploratory endeavors solely by whether they fulfilled their original intention. Many of the most profound contributions to human knowledge emerged from projects that “failed” in their stated goals but succeeded in generating new paradigms, tools, or insights.

Case Studies in Productive Failure

Sources: Perkin's dye from Connections by James Burke; Witten quote from Closer to the Truth (2021).

Philosophical Anchors

• Karl Popper: Even failed theories contribute by being falsifiable and refining the boundary of what's testable.
• Thomas Kuhn: Paradigm shifts often arise from anomalies---failures that don't fit the current model.
• Paul Feyerabend: Scientific progress is messy, pluralistic, and often driven by deviation from norms.

Meta-Lesson: Reframing Failure as Discovery

• Constructive vs. Principle Theories: Einstein's shift is emblematic of how abandoning a flawed framework can open the door to deeper truths.
• Serendipity and Constraint: Many breakthroughs arise when constraints force a change in approach or reveal hidden structure.
• Symbolic Closure: Projects like Biosphere 2 ritualize the complexity of Earth systems, even if they don't "solve" them.

Proposal: Honor Emergent Knowledge

Let's imagine a symbolic "PhD" not just for individuals, but for projects that advanced human understanding through unexpected pathways. Biosphere 2 and string theory would be prime candidates---not for what they proved, but for what they provoked.

Afterword: