The Rise of AI: Why the Rote Professions Are on the Chopping Block

Medical doctors, lawyers, and judges have been the undisputed titans of professional authority for centuries. Their expertise, we are told, is sacrosanct, earned through gruelling education, prodigious memory, and painstaking application of established knowledge. But peel back the robes and white coats, and you’ll find something unsettling: a deep reliance on rote learning—an intellectual treadmill prioritising recall over reasoning. In an age where artificial intelligence can memorise and synthesise at scale, this dependence on predictable, replicable processes makes these professions ripe for automation.

Rote Professions in AI’s Crosshairs

AI thrives in environments that value pattern recognition, procedural consistency, and brute-force memory—the hallmarks of medical and legal practice.

  1. Medicine: The Diagnosis Factory
    Despite its life-saving veneer, medicine is largely a game of matching symptoms to diagnoses, dosing regimens, and protocols. Enter an AI with access to the sum of human medical knowledge: not only does it diagnose faster, but it also skips the inefficiencies of human memory, emotional bias, and fatigue. Sure, we still need trauma surgeons and such, but diagnosticians are so yesterday’s news.
    Why pay a six-figure salary to someone recalling pharmacology tables when AI can recall them perfectly every time? Future healthcare models are likely to see Medical Technicians replacing high-cost doctors. These techs, trained to gather patient data and operate alongside AI diagnostic systems, will be cheaper, faster, and—ironically—more consistent.
  2. Law: The Precedent Machine
    Lawyers, too, sit precariously on the rote-learning precipice. Case law is a glorified memory game: citing the right precedent, drafting contracts based on templates, and arguing within frameworks so well-trodden that they resemble legal Mad Libs. AI, with its infinite recall and ability to synthesise case law across jurisdictions, makes human attorneys seem quaintly inefficient. The future isn’t lawyers furiously flipping through books—it’s Legal Technicians trained to upload case facts, cross-check statutes, and act as intermediaries between clients and the system. The $500-per-hour billable rate? A relic of a pre-algorithmic era.
  3. Judges: Justice, Blind and Algorithmic
    The bench isn’t safe, either. Judicial reasoning, at its core, is rule-based logic applied with varying degrees of bias. Once AI can reliably parse case law, evidence, and statutes while factoring in safeguards for fairness, why retain expensive and potentially biased judges? An AI judge, governed by a logic verification layer and monitored for compliance with established legal frameworks, could render verdicts untainted by ego or prejudice.
    Wouldn’t justice be more blind without a human in the equation?

The Techs Will Rise

Replacing professionals with AI doesn’t mean removing the human element entirely. Instead, it redefines roles, creating new, lower-cost positions such as Medical and Legal Technicians. These workers will:

  • Collect and input data into AI systems.
  • Act as liaisons between AI outputs and human clients or patients.
  • Provide emotional support—something AI still struggles to deliver effectively.

The shift also democratises expertise. Why restrict life-saving diagnostics or legal advice to those who can afford traditional professionals when AI-driven systems make these services cheaper and more accessible?

But Can AI Handle This? A Call for Logic Layers

AI critics often point to hallucinations and errors as proof of its limitations, but this objection is shortsighted. What’s needed is a logic layer: a system that verifies whether the AI’s conclusions follow rationally from its inputs.

  • In law, this could ensure AI judgments align with precedent and statute.
  • In medicine, it could cross-check diagnoses against the DSM, treatment protocols, and patient data.

A second fact-verification layer could further bolster reliability, scanning conclusions for factual inconsistencies. Together, these layers would mitigate the risks of automation while enabling AI to confidently replace rote professionals.

Resistance and the Real Battle Ahead

Predictably, the entrenched elites of medicine, law, and the judiciary will resist these changes. After all, their prestige and salaries are predicated on the illusion that their roles are irreplaceable. But history isn’t on their side. Industries driven by memorisation and routine application—think bank tellers, travel agents, and factory workers—have already been disrupted by technology. Why should these professions be exempt?

The real challenge lies not in whether AI can replace these roles but in public trust and regulatory inertia. The transformation will be swift and irreversible once safeguards are implemented and AI earns confidence.

Critical Thinking: The Human Stronghold

Professions that thrive on unstructured problem-solving, creativity, and emotional intelligence—artists, philosophers, innovators—will remain AI-resistant, at least for now. But the rote professions, with their dependency on standardisation and precedent, have no such immunity. And that is precisely why they are AI’s lowest-hanging fruit.

It’s time to stop pretending that memorisation is intelligence, that precedent is innovation, or that authority lies in a gown or white coat. AI isn’t here to make humans obsolete; it’s here to liberate us from the tyranny of rote. For those willing to adapt, the future looks bright. For the rest? The machines are coming—and they’re cheaper, faster, and better at your job.

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.