If you want to understand the underlying technology, this video explains the concept of Reinforcement Learning from Human Feedback (RLHF) pretty well.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Are there efforts to improve ChatGPT for Julia code? | 26 | 4165 | July 24, 2023 | |
| LLM AI just for Julia? A proposal: Julia *plus* science LLM? | 4 | 1695 | June 24, 2023 | |
| AI tools to write (Julia) code (best/worse experience), e.g. ChatGPT, GPT 3.5 | 62 | 17020 | May 14, 2024 | |
| Julia ranking fairly good in code generating using ChatGPT | 3 | 1486 | November 19, 2023 | |
| Is Bard better at writing Julia than ChatGPT? | 3 | 388 | July 14, 2023 |