OpenAI Blog company blog
Aligning Language Models to Follow Instructions
We’ve trained language models that are much better at following user intentions than GPT-3 while also making them more truthful and less toxic, using techniques developed through our alignment research. These InstructGPT models, which are trained with humans in the loop, are now deployed as the default language models…
- Points
- 59
- HN comments
- 6
- Submissions
- 1
- Cited by
- 16 commenters
AI & Machine LearningSoftware Engineering2022
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Jan 27, 2022 | Aligning Language Models to Follow Instructions by todsacerdoti | 59 | 6 |
Cited in comments
Linked from 17 Hacker News comments by 16 different people, from Feb 2022 to Feb 2023.
Most recent:
- txtai · Feb 4, 2023
- BoorishBears · Jan 29, 2023
- sthatipamala · Jan 14, 2023
- Terretta · Jan 10, 2023
- narrator · Dec 30, 2022
- swyx · Dec 29, 2022
