Great article from Pangram on why LLM-generated text remains detectable.
In other words: the more models become "good assistants", the more recognizable their writing style can become.
Worth a read.
Link below π
Gmail is FREE
TikTok is FREE
Google is FREE
Chrome is FREE
YouTube is FREE
ChatGPT is FREE
Facebook is FREE
Instagram is FREE
WhatsApp is FREE
You pay with your personal data.