The Trouble with Facts

5–8 minutes

One Motor Vehicle

What we call facts are not discoveries of an unfiltered world. They are the end-products of mediation.

Let’s walk through an example.

Image: Autosmash example. An observer arrives with experience – from genetic predisposition to childhood trauma to winning the lottery. Whatever it might be. Of course, they have many cognitive deficits, biases and filters. Then, there’s the immediate problem of attention. When did they notice the event? Did they turn to look after hearing the noise, or were they meditating on the tree in that moment?

Apparently, a motor vehicle has collided with a tree. Trees are immobile objects, so we can safely rule out the tree colliding with the car.*

So what, exactly, are the facts?

Audio: NotebookLM summary podcast of this topic.

Ontology (the boring bit)

Ontologically, something happened.

A car struck a tree.
Metal deformed.
Momentum stopped.

Reality did not hesitate. It did not consult witnesses. It did not await interpretation.

This is the part Modernity likes to gesture at reverently before immediately leaving it behind.

Image: Requisite NotebookLM infographic on this content.

The Witness

Even the driver does not enjoy privileged access to “what really happened”.

They get:

  • proprioceptive shock
  • adrenaline distortion
  • attentional narrowing
  • selective memory
  • post hoc rationalisation
  • possibly a concussion

Which is already several layers deep before language even arrives to finish the job.

We can generalise the structure:

Ontology: events occur. States of affairs obtain. Something happens whether or not we notice.

Epistemology: observation is always filtered through instruments, concepts, language, habits, and incentives.

Modern sleight of hand: collapse the second into the first and call the result the facts.

People love the phrase “hard facts”, as if hardness transfers from objects to propositions by osmosis. It doesn’t. The tree is solid. The fact is not.

Facts are artefacts. They are assembled from observation, inference, convention, and agreement. They function. They do not reveal essence.

Filtration

An event occurred. A car struck a tree.

Then an observer arrives. But observers never arrive empty-handed.

They arrive with history: genetics, upbringing, trauma, habits, expectations, incentives. They arrive already filtered.

Daniel Kahneman, Olivier Sibony, and Cass Sunstein spend an entire book explaining just how unreliable this process is. See Noise: A Flaw in Human Judgment if you want the empirical receipts.

  • Even before bias enters, attention does.
  • When did the observer notice the crash?
  • At the sound? At the sight? After the fact?
  • Were they already looking, or did the noise interrupt something else entirely?

Reality happens once. Facts happen many times, differently, depending on who needs them and why.

Here Comes the Law

This is where the legal system enters, not because truth has been found, but because closure is required.

Courts do not discover facts. They designate versions of events that are good enough to carry consequences. They halt the cascade of interpretations by institutional force and call the result justice.

At every epistemic level, what we assert are interpretations of fact, never access to ontological essence.

Intent, negligence, recklessness. These are not observations. They are attributions. They are stopping rules that allow systems to function despite uncertainty.

The law does not ask what really happened.
It asks which story is actionable.

Two Motor Vehicles

Now add a second moving object.

Another car enters the frame, and with it an entire moral universe.

Suddenly, the event is no longer merely physical. It becomes relational. Agency proliferates. Narratives metastasise.

Who was speeding?
Who had the right of way?
Who saw whom first?
Who should have anticipated whom?

Intent and motive rush in to fill the explanatory vacuum, despite remaining just as unobservable as before.

Nothing about the ontology improved.
Everything about the storytelling did.

Where the tree refused intention, the second vehicle invites it. We begin inferring states of mind from trajectories, attributing beliefs from brake lights, extracting motives from milliseconds of motion.

But none of this is observed.

What we observe are:

  • vehicle positions after the fact,
  • damage patterns,
  • skid marks,
  • witness statements already filtered through shock and expectation.

From these traces, we construct mental interiors.

The driver “intended” to turn.
The other driver “failed” to anticipate.
Someone was “reckless”.
Someone else was merely “unlucky”.

These are not facts. They are interpretive assignments, layered atop already mediated observations, selected because they allow responsibility to be distributed in socially recognisable ways.

This is why explanation now fractures.

One cascade of whys produces a story about distraction or poor judgment.
Another produces a story about road design or visibility.
Another about timing, traffic flow, or urban planning.

Each narrative is plausible.
Each is evidence-constrained.
None is ontologically privileged.

Yet one will be chosen.

Not because it is truer, but because it is actionable.

The presence of a second vehicle does not clarify causation. It merely increases the number of places we are willing to stop asking questions.

Modernity mistakes this proliferation of narrative for epistemic progress. In reality, it is moral bookkeeping.

The crash still occurred.
Metal still deformed.
Momentum still stopped.

What changed was not access to truth, but the urgency to assign fault.

With one vehicle and a tree, facts already fail to arrive unmediated.
With two vehicles, mediation becomes the point.

And still, we insist on calling the result the facts.

Many Vehicles, Cameras, and Experts

At this point, Modernity regains confidence.

Add more vehicles.
Add traffic cameras.
Add dashcams, CCTV, bodycams.
Add accident reconstruction experts, engineers, psychologists, statisticians.

Surely now we are approaching the facts.

But nothing fundamental has changed. We have not escaped mediation. We have merely scaled it up and professionalised it.

Cameras do not record reality. They record:

  • a frame,
  • from a position,
  • at a sampling rate,
  • with compression,
  • under lighting conditions,
  • interpreted later by someone with a mandate.

Video feels decisive because it is vivid, not because it is ontologically transparent. It freezes perspective and mistakes that freeze for truth. Slow motion, zoom, annotation. Each step adds clarity and distance at the same time.

Experts do not access essence either. They perform disciplined abduction.

From angles, debris fields, timing estimates, and damage profiles, they infer plausible sequences. They do not recover the event. They model it. Their authority lies not in proximity to reality, but in institutional trust and methodological constraint.

More data does not collapse interpretation.
It multiplies it.

With enough footage, we don’t get the story. We get competing reconstructions, each internally coherent, each technically defensible, each aligned to a different question:

  • Who is legally liable?
  • Who is financially responsible?
  • Who violated policy?
  • Who can be blamed without destabilising the system?

At some point, someone declares the evidence “clear”.

What they mean is: we have enough material to stop arguing.

This is the final Modern illusion: that accumulation converges on essence. In reality, accumulation converges on closure.

The event remains what it always was: inaccessible except through traces.
The facts become thicker, more confident, more footnoted.
Their metaphysical status does not improve.

Reality happened once. It left debris. We organised the debris into narratives that could survive institutions.

Cameras didn’t reveal the truth. Experts didn’t extract it. They helped us agree on which interpretation would count.

And agreement, however necessary, has never been the same thing as access to what is.

* I was once driving in a storm, and a telephone pole fell about a metre in front of my vehicle. My car drove over the pole, and although I was able to drive the remainder of the way home, my suspension and undercarriage were worse for the wear and tear.

The Enlightenment Sleight of Hand

How Reason Inherited God’s Metaphysics.

The Enlightenment, we are told, was the age of Reason. A radiant exorcism of superstition. Out went God. Out went angels, miracles, saints, indulgences. All that frothy medieval sentiment was swept aside by a brave new world of logic, science, and progress. Or so the story goes.

Audio: NotebookLM podcast on this topic.

But look closer, and you’ll find that Reason didn’t kill God—it absorbed Him. The Enlightenment didn’t abandon metaphysics. It merely privatised it.

From Confessional to Courtroom

We like to imagine that the Enlightenment was a clean break from theology. But really, it was a semantic shell game. The soul was rebranded as the self. Sin became crime. Divine judgement was outsourced to the state.

We stopped praying for salvation and started pleading not guilty.

The entire judicial apparatus—mens rea, culpability, desert, retribution—is built on theological scaffolding. The only thing missing is a sermon and a psalm.

Where theology had the guilty soul, Enlightenment law invented the guilty mind—mens rea—a notion so nebulous it requires clairvoyant jurors to divine intention from action. And where the Church offered Hell, the state offers prison. It’s the same moral ritual, just better lit.

Galen Strawson and the Death of Moral Responsibility

Enter Galen Strawson, that glowering spectre at the feast of moral philosophy. His Basic Argument is elegantly devastating:

  1. You do what you do because of the way you are.
  2. You can’t be ultimately responsible for the way you are.
  3. Therefore, you can’t be ultimately responsible for what you do.

Unless you are causa sui—the cause of yourself, an unmoved mover in Calvin Klein—you cannot be held truly responsible. Free will collapses, moral responsibility evaporates, and retributive justice is exposed as epistemological theatre.

In this light, our whole legal structure is little more than rebranded divine vengeance. A vestigial organ from our theocratic past, now enforced by cops instead of clerics.

The Modern State: A Haunted House

What we have, then, is a society that has denied the gods but kept their moral logic. We tossed out theology, but we held onto metaphysical concepts like intent, desert, and blame—concepts that do not survive contact with determinism.

We are living in the afterglow of divine judgement, pretending it’s sunlight.

Nietzsche saw it coming, of course. He warned that killing God would plunge us into existential darkness unless we had the courage to also kill the values propped up by His corpse. We did the first bit. We’re still bottling it on the second.

If Not Retribution, Then What?

Let’s be clear: no one’s suggesting we stop responding to harm. But responses should be grounded in outcomes, not outrage.

Containment, not condemnation.

Prevention, not penance.

Recalibration, not revenge.

We don’t need “justice” in the retributive sense. We need functional ethics, rooted in compassion and consequence, not in Bronze Age morality clumsily duct-taped to Enlightenment reason.

The Risk of Letting Go

Of course, this is terrifying. The current system gives us moral closure. A verdict. A villain. A vanishing point for our collective discomfort.

Abandoning retribution means giving that up. It means accepting that there are no true villains—only configurations of causes. That punishment is often revenge in drag. That morality itself might be a control mechanism, not a universal truth.

But if we’re serious about living in a post-theological age, we must stop playing dress-up with divine concepts. The Enlightenment didn’t finish the job. It changed the costumes, kept the plot, and called it civilisation.

It’s time we staged a rewrite.

Democracy: Judge and Jury

As I make progress on my Democracy: The Great Illusion book, I am working on a chapter considering juries as a microcosm of a democratic process. I am debating whether to include this information in the chapter, Like the justice system in the United States, perhaps I should just flip a coin.

Having been seated on three juries in my lifetime, it was just as I had expected. Thankfully, I’ve never been on the other side of this Russian Roulette revolver. We really need to limit human-based decision systems. I have as much faith in juries as I have with democracies, but I thought I might take a peek into deliberation at a smaller scale, perhaps 12 jurors.

I read Kahneman’s Noise: A Flaw in Human Judgment when it was published in 2021, and I was not at all surprised how trial outcomes, quite often led to markedly different outcomes depending on the judge and the defendant. Although discrepancies based on sex and race have been well documented, this book showcased how much the judge’s mood affected sentencing—particularly if s/he was hungry. But this was not my interest.

My interest was to assess how the same case might fare given different judges and juries, so I asked ChatGPT. I want to share what it had to say—edited slightly for readability and flow.

ChatGPT Transcript

There have been several studies and controlled experiments assessing the variability in trial outcomes when the same case is tried separately by different judges and juries. These studies aim to evaluate the consistency and reliability of judicial decision-making, shedding light on the fallibility and variability of trial outcomes. Here are some key findings from such research:

Studies on Judicial and Jury Variability

The American Jury Study

One of the most notable studies is “The American Jury” by Harry Kalven and Hans Zeisel. This extensive study compared the decisions of juries and judges in actual cases. It found that juries and judges often agree on verdicts, but there are significant instances where they disagree. This disagreement highlights the subjective nature of decision-making and the potential for variability in trial outcomes.

Judge-Jury Agreement

Research by Valerie Hans and Neil Vidmar in “Judging the Jury” indicates that judges and juries reach the same verdict about 75-80% of the time. However, in the remaining 20-25% of cases, the disagreement can lead to different outcomes for the same case. These findings suggest that personal interpretations and biases can influence verdicts.

The Civil Jury Project

The Civil Jury Project at NYU School of Law has conducted several studies examining jury decision-making. Their research has highlighted how factors like juror demographics, pre-existing biases, and the presentation of evidence can lead to different outcomes in similar cases.

Controlled Experiments

Controlled experiments, such as those conducted by Shari Seidman Diamond and her colleagues, have involved mock trials where participants (acting as jurors) are presented with the same case. These experiments have shown significant variability in verdicts and sentences, demonstrating the influence of group dynamics, individual biases, and the presentation of evidence on jury decisions.

Key Findings

Cognitive Bias and Heuristics

Studies indicate that cognitive biases and heuristics significantly impact both judges and juries. Biases such as the anchoring effect, where the initial piece of evidence presented influences subsequent judgments, can lead to different outcomes for the same case.

Case Complexity and Juror Understanding

Research has shown that the complexity of legal cases can lead to variability in outcomes. Jurors often struggle with understanding complex legal and technical issues, leading to decisions based on incomplete or misunderstood information.

Influence of Legal Instructions

The clarity and comprehensibility of legal instructions given to juries play a crucial role in decision-making. Studies have found that poorly understood instructions can result in inconsistent application of the law, leading to variable outcomes.

Implications

The variability in trial outcomes highlights the fallibility of judicial processes and underscores the importance of reforms to enhance consistency and fairness. Potential reforms could include:

  1. Improving Juror Education: Providing better education and resources for jurors to understand legal principles and case-specific details.
  2. Reducing Cognitive Bias: Implementing measures to mitigate cognitive biases, such as standardized jury instructions and blind procedures.
  3. Enhancing Legal Instructions: Ensuring that legal instructions are clear, concise, and comprehensible to prevent misinterpretation.
  4. Utilizing Expert Testimony: Increasing the use of expert testimony to clarify complex issues for jurors.

Conclusion

The variability in trial outcomes, when the same case is tried by different judges and juries, underscores the need for ongoing research and reform in judicial processes. By understanding the factors that contribute to inconsistent verdicts, we can develop strategies to enhance the fairness and reliability of the justice system.

References

  • Kalven, H., & Zeisel, H. (1966). The American Jury. Little, Brown and Company.
  • Hans, V., & Vidmar, N. (1986). Judging the Jury. Plenum Press.
  • Diamond, S. S., & Rose, M. R. (2005). Real Juries: The Power of Watching. Basic Books.
  • The Civil Jury Project at NYU School of Law. (n.d.). Research on Jury Decision Making. Retrieved from [website].
  • Kahneman, D., Sibony, O., & Sunstein, C. R. (2021). Noise: A Flaw in Human Judgment. Little, Brown Spark.

Humans Ruin the Economy

Humans are ruining the economy.

Podcast: Audio rendition of this page content.

This is the caption on the sign for this segment. The sign advertises a solution, which is to “Vote for DEMOCROBOT… The first party run by artificial intelligence”. It also promises to “give everyone a living wage of ÂŁ1436.78 a week”.

I have been very vocal that I find the idea of humans governing humans is a bad idea at the start. By and large, humans are abysmal system thinkers and easily get lost in complexity. This is why our governments and economies require so much external energy and course correction. Not only were they poorly designed and implemented, but they’re also trying to manage a dynamic system—a complex system. It won’t work.

What about bots and artificial intelligence? The above image was posted elsewhere, and a person commented that our governments are already filled with artificial intelligence. I argued that at best we’ve got pseudo-intelligence; at worse, we’ve got artificial pseudo-intelligence, API.

The challenge with AI is that it’s developed by humans with all of their faults and biases in-built.

The challenge with AI is that it’s developed by humans with all of their faults and biases in-built. On the upside, at least in theory, rules could be created to afford consistency and escape political theatre. The same could be extended to the justice system, but I’ll not range there.

Part of the challenge is that the AI needs to optimise several factors, at least, and not all factors are measurable or can be quantified. Any such attempt would tip the playing field one way or another. We might assume that at least AI would be unreceptive to lobbying and meddling, but would this be the case? AI—or rather ML, Machine Learning or DL, Deep Learning—rely on input. It wouldn’t take long for interested think tanks to flood the source of inputs with misinformation. And if there is an information curator, we’ve got a principle-agent problem—who’s watching the watcher?—, and we may need to invoke Jeremy Bentham’s Panopticon solution.

One might even argue that an open-source, independently audited system would work. Who would be auditing and whose interpretation and opinion would we trust? Then I think of Enron and Worldcom. Auditors paid to falsify their audit results. I’d also argue that this would cause a shift from the political class to the tech class, but the political class is already several tiers down and below the tech class, so the oligarchs still win.

This seems to be little more than a free-association rant, so I’ll pile on one more reflection. Google and Facebook (or Meta) have ethical governing bodies that are summarily shunned or simply ignored when they point out that the parent company is inherently unethical or immoral. I wouldn’t expect much difference here.

I need a bot to help write my posts. I’ll end here.