From avoid-ai-writing
AI writing, evaluated
avoid-ai-writing is a pattern catalog and detector for the tells that give AI-generated text away. It exists because a model optimized for plausibility will produce something that reads correct whether or not it is.
That problem is the throughline of this show. Three conversations if you want the argument underneath the tool:
-
Why LLMs Are Plausibility Engines, Not Truth Engines
“If it’s plausible enough, it’s going to be indistinguishable from the truth.”
The clearest statement of the problem the detector exists for. A model trained to produce likely text is not trained to produce true text, and past a certain quality the two stop being separable by reading.
-
Hallucinations Are a Data Architecture Problem
The case that hallucination is a failure in the retrieval layer rather than a flaw in the model, which changes where you go looking when the output is confidently wrong.
-
Every AI Agent Has an Evaluation Gap
Everyone says their system works; almost nobody can say what “works” means in a number. The same reason a detector you can run beats a vibe check.
What this is
Chain of Thought is where builders reason through what's changing in AI and software infrastructure. Every episode carries its full transcript on the page, so you can read one instead of listening to it.
Recent guests
