For example “AI Writer” is built on GPT-2 transformer-based language model with 1.5 billion parameters, trained on a dataset of 8 million web pages. It is trained to predict the next word, given all of the previous words within some text. You can read more on it here: https://openai.com/blog/better-language-models/
Another interesting feature is “AI Heatmap”. Basically, we took two different datasets to train our model: a dataset from an eye-tracking device and dataset gathered by using BubbleView methodology. More on BubbleView here: https://bubbleview.namwkim.org/
For example “AI Writer” is built on GPT-2 transformer-based language model with 1.5 billion parameters, trained on a dataset of 8 million web pages. It is trained to predict the next word, given all of the previous words within some text. You can read more on it here: https://openai.com/blog/better-language-models/
Another interesting feature is “AI Heatmap”. Basically, we took two different datasets to train our model: a dataset from an eye-tracking device and dataset gathered by using BubbleView methodology. More on BubbleView here: https://bubbleview.namwkim.org/