Computer Science student interested in Machine Learning

Joined July 2020
Please note that the first generation of any AI Dungeon prompt is GPT-2, and that the AI Dungeon model has been tweaked in various ways from the base GPT-3 model (including fine-tuning on adventure stories)
0
0
0
2
Note: GPT-3 was trained on common crawl ending in 2019, and so could not have "obtained most of its word patterns" from articles published in 2020. The human quality experiment used stories GPT-3 hadn't trained on (from the "future"). It was given only titles and subtitles.
0
0
0
0
Replying to @nickwalton00
Are there any other differences you can tell us about? Prepending, separating, or wrapping input? Fine tuning on some story focused corpus? Context size limits? Something else?
1
0
0
1
Derek McKay retweeted
I've noticed a number of people using AI Dungeon to test GPT-3's abilities. While it's a great way to see how GPT-3 can power an interesting application. It's a poor test of GPT-3's abilities in general. The first generation of any custom prompt is actually GPT-2.
19
27
11
169
Show this thread
I only have access to AI dungeon's Dragon model, but I've had some success asking the AI to "spell out" it's thoughts step by step. Here are some simple chain rule applications.
0
0
0
0