Supreme Court Reverses Appellate Judgment After AI Flags Procedural Error
🔎 What Happened
A Korean legal-tech AI analyzed an appellate criminal judgment and identified a procedural error the appellate court had overlooked. The defense adopted the AI-flagged issue as a ground of appeal, and the Supreme Court reversed and remanded the case.
This marks the Supreme Court’s first explicit ruling on whether a court may resolve a post-sentencing concurrence (사후적 경합범) through judgment correction rather than reversal and resentencing.
—
⚖️ Case Background
The defendant committed multiple drunk-driving offenses over time.
While one case was pending on appeal, another drunk-driving conviction became final.
This created a post-sentencing concurrence relationship: crimes committed before a prior judgment became final, but sentenced afterward.
The trial court imposed a custodial sentence considering sentencing equity.
The appellate court dismissed the appeal and attempted to address the new concurrence issue via 판결 경정 (judgment correction).
—
❗ The Legal Problem
Judgment correction is permitted only for obvious clerical or calculation errors.
The question:
> When a post-sentencing concurrence arises mid-appeal, can the appellate court fix the judgment by “correction,” or must it reverse ex officio and resentence?
—
🤖 Role of AI (as reported)
The AI:
Detected that a post-sentencing concurrence had crystallized after the trial judgment.
Flagged that handling it through judgment correction exceeded procedural limits.
Suggested an appeal strategy arguing misunderstanding of law affecting the judgment.
Predicted a high likelihood of reversal due to procedural defect, regardless of whether the final sentence might remain unchanged.
—
🧑⚖️ Supreme Court Holding
The Supreme Court reversed and remanded, holding that:
Adding a post-sentencing concurrence and its legal consequences through judgment correction amounts to a substantive modification of the original judgment.
Such modification exceeds the permissible scope of correction.
Even if the resentencing result could be identical, the court must follow the proper procedural route, including correct concurrence handling and resentencing.
Failure to do so constitutes a legal error affecting the judgment.
—
📌 Why This Matters
Procedure over outcome: Courts must follow the correct process even if the sentence would not change.
Clear boundary set: Appellate courts cannot use judgment correction to bypass required resentencing steps in post-sentencing concurrence cases.
Legal-tech signal: Demonstrates a concrete use case where AI functions as a procedural issue-spotter, not a decision-maker.
Precedential value: First Supreme Court guidance on this precise procedural question.
—
🧾 Takeaway
> In post-sentencing concurrence cases, shortcuts are not allowed.
Correction is not a substitute for reversal and resentencing.
Article: https://www.lawtimes.co.kr/news/214742
*I chatted briefly with my friend Chet (GPT) about this.
Chet :
Here’s my plain-spoken, honest* take on the situation described in that KlawGuru article — where the Supreme Court reversed an appellate decision after an AI tool flagged a procedural error:
🧠 Big Picture
AI in this case didn’t decide the outcome — it spotted a procedural defect (specifically that an appellate court used judgment correction where reversal and resentencing were procedurally required). The Supreme Court agreed and reversed and remanded on that basis.
This strikes me as healthy legal evolution, not a scary “AI is running the courts” moment.
⚖️ What’s Right About This
1. Procedural correctness matters more than convenient outcomes
The story underscores a core rule of law principle: courts must follow proper procedures even if the ultimate sentence might be the same. The Supreme Court reaffirmed that you can’t bypass procedural safeguards just because the result seems fair.
That’s subtle — but essential — because procedures exist not for efficiency but to protect due process and legal certainty.
2. AI as a spotter, not a decider
In this case, the AI flagged something a human lawyer might otherwise overlook. That suggests a niche where AI augments human lawyers rather than replaces them. The AI didn’t write the Supreme Court’s opinion — it helped frame the argument about the procedural error.
3. Guardrails are evolving, not collapsing
We are hearing more and more about courts and lawyers misusing AI — hallucinated citations, invented cases, faulty reasoning — and the legal world is responding with warnings and rule reviews.
That suggests this isn’t a free-for-all; it’s a dialogue between technology and legal norms.
🤔 But There Are Legitimate Concerns
1. AI hallucination risk
AI sounds authoritative even when it’s wrong — and courts or lawyers who don’t verify could propagate serious errors. That’s not hypothetical; lawyers have already been sanctioned for filing briefs citing fake cases generated by AI.
This means reliance without verification is dangerous and could erode trust in judicial accuracy.
2. Judges and procedural nuance
Judges aren’t trained to treat AI outputs as gospel, but we’re seeing instances where courts or lawyers lean on AI without cross-checking. That’s precarious precisely because procedural rules are the backbone of fairness.
🔍 My Bottom Line (Honest)
The real story here isn’t AI supplanting legal judgment. It’s that technology can flag issues, but human judgment — and procedural discipline — still decide the case. The Supreme Court’s intervention reinforces that:
Human courts remain the final authority.
AI is a tool, not a substitute for legal reasoning.
Procedural rigor matters above all.
If this case becomes a paradigm for careful, verified AI use in procedural spotting, it could be a net positive. But if people start treating AI as a shortcut without verification, that’s where trouble begins.
So I’d describe this as cautiously optimistic for AI’s role in law: useful when used with discipline, risky when used uncritically.
KLAWGURU.COM 