Template:Did you know nominations/Reinforcement learning from human feedback
- The following is an archived discussion of the DYK nomination of the article below. Please do not modify this page. Subsequent comments should be made on the appropriate discussion page (such as this nomination's talk page, the article's talk page or Wikipedia talk:Did you know), unless there is consensus to re-open the discussion at this page. No further edits should be made to this page.
The result was: promoted by Hilst talk 14:19, 12 April 2024 (UTC)
| DYK toolbox |
|---|
Reinforcement learning from human feedback
- ... that artificial intelligence models like ChatGPT can learn from human feedback? Source: "That’s because OpenAI has used a technique in ChatGPT called reinforcement learning from human feedback, which improves the model’s answers based on feedback from users." [1]
- Reviewed:
Improved to Good Article status by PopoDameron (talk).
Number of QPQs required: 0. Nominator has less than 5 past nominations.
Post-promotion hook changes will be logged on the talk page; consider watching the nomination until the hook appears on the Main Page.popodameron talk 00:08, 2 April 2024 (UTC).
New GA, and hook is interesting and long enough. Source provided (MIT Technology Review) is reliable. No QPQ is needed for now. Article is properly sourced, and Earwig did not return any plagiarism concerns, so everything should be ok. Passing this nomination. Good job! Davest3r08 >:3 (talk) 14:46, 4 April 2024 (UTC)