Raschka Tutorial Builds AI Text Detector and Evasion Trainer
Sebastian Raschka published a tutorial explaining how to build a simple AI text detector from scratch, inspired by Substack's new AI detector feature. The detector is also used as a verifier to train a small language model to produce text that evades detection, serving as an educational project to study detector limitations and verifier-based LLM applications.
Coverage timeline
Ahead of AI (Raschka)Sebastian Raschka, PhD
Substack recently launched its AI detector feature in the UI, which is super interesting. Separately, lots of people asked me about interesting local do-it-yourself LLM projects as demos to show what small language models (SLMs) are capable of. Putting one and one together, I thought it would be interesting to show how an AI detector can be implemented. I will also use it as a verifier to train a small language model to produce text that avoids detection. This is a small educational project for studying the limitations of AI detectors and exploring a verifier-based LLM application beyond regular reasoning models trained on math and code. Figure 1: Substack now features a built-in AI detector. So, as mentioned above, the intended goal of this tutorial is to explain how AI detectors work by building (a simple) one. In practice, such a detector can be used to filter out spammy content, but also to potentially improve your personal writing without turning it into AI-generated text. For exa
