Agenda

1. 05:00 - How AI Dungeon is used with GPT3 engine
2. 13:00 - Frequency penalty vs. Presence penalty Settings
3. 18:21 - Doing detect and regenerate settings
4. 25:30 - Customer influence responses
5. 30:00 - Gpt3 to use in summarization
6. 33:00 - Trevor exits the call
7. 33: 50 - Nick’s experiences between GPT2 and GPT3
8. 36:00 - Sampling Process
9. 40:00 - Using machine learning for other things
10. 41:00 - What is AI Dungeon?
11. 46:00 - Quests
12. 52:00 - Give a little overview on how AI Dungeon works now

Notes

• Fine tuning can make a great difference
• Safe mode - that’s on by default - reduces the chances of having an explicit token in the Space
• Detection on the user side - Child Friendly version