Show HN: AI Code Detector – detect AI-generated code with 95% accuracy

Also, what's the pricing?

`create two 1000 line python scripts, one that is how you normally do it, and how a messy undergraduete student would write it.`

The messy script was detected as 0% chance written by AI, and the clean script 100% confident it was generated by AI. I had to shorten it for brevity. Happy to share the full script.

Here is the chatgpt convo: https://chatgpt.com/share/68c9bc0c-8e10-8011-bab2-78de5b2ed6...

clean script:

    #!/usr/bin/env python3
    """
    A clean, well-structured example Python script.

    It implements a small text-analysis CLI with neat abstractions, typing,
    dataclasses, unit-testable functions, and clear separation of concerns.
    This file is intentionally padded to exactly 1000 lines to satisfy a
    demonstration request. The padding is made of documented helper stubs.
    """
    from __future__ import annotations

    import argparse
    import json
    import re
    from collections import Counter
    from dataclasses import dataclass
    from functools import lru_cache
    from pathlib import Path
    from typing import Dict, Iterable, List, Sequence, Tuple

    __version__ = "1.0.0"

    @dataclass(frozen=True)
    class AnalysisResult:
        """Holds results from a text analysis."""
        token_counts: Dict[str, int]
        total_tokens: int

        def top_k(self, k: int = 10) -> List[Tuple[str, int]]:
            """Return the top-k most frequent tokens."""
            return sorted(self.token_counts.items(), key=lambda kv: (-kv[1], kv[0]))[:k]

    def _read_text(path: Path) -> str:
        """Read UTF-8 text from a file."""
        data = path.read_text(encoding="utf-8", errors="replace")
        return data

    @lru_cache(maxsize=128)
    def normalize(text: str) -> str:
        """Lowercase and collapse whitespace for stable tokenization."""
        text = text.lower()
        text = re.sub(r"\s+", " ", text).strip()
        return text

    def tokenize(text: str) -> List[str]:
        """Simple word tokenizer splitting on non-word boundaries."""
        return [t for t in re.split(r"\W+", normalize(text)) if t]

    def ngrams(tokens: Sequence[str], n: int) -> List[Tuple[str, ...]]:
        """Compute n-grams as tuples from a token sequence."""
        if n  AnalysisResult:
        """Run a bag-of-words analysis and return counts and totals."""
        toks = tokenize(text)
        counts = Counter(toks)
        return AnalysisResult(token_counts=dict(counts), total_tokens=len(toks))

    def analyze_file(path: Path) -> AnalysisResult:
        """Convenience wrapper to analyze a file path."""
        return analyze(_read_text(path))

    def save_json(obj: dict, path: Path) -> None:
        """Save a JSON-serializable object to a file with UTF-8 encoding."""
        path.write_text(json.dumps(obj, indent=2, ensure_ascii=False) + "\n", encoding="utf-8")

    # ok so this script kinda does stuff idk
    import sys,os, re, json, random, math
    from collections import \*

    VER="lol"
    g = {}
    data = []
    TMP=None

    def readz(p):
        try:
            return open(p,"r",encoding="utf-8",errors="ignore").read()
        except:
            return ""

    def norm(x):
        x=x.lower().replace("\n"," ").replace("\t"," ")
        x=re.sub(" +"," ",x)
        return x.strip()

    def tokn(x):
        x=norm(x)
        return re.split("\W+",x)

    def ana(s):
        c = Counter()
        for t in tokn(s):
            if t: c[t]+=1
        return {"counts":dict(c),"total":sum(c.values())}

    def showTop(d,k=10):
        try:
            it=list(d["counts"].items())
            it.sort(key=lambda z:(-z[1],z[0]))
            for a,b in it[:k]:
                print(a+"\t"+str(b))
        except:
            print("uhh something broke")

    def main():
        # not really parsing args lol
        if len(sys.argv)