OpenAI Blog company blog
Improving mathematical reasoning with process supervision
We’ve trained a model to achieve a new state-of-the-art in mathematical problem solving by rewarding each correct step of reasoning (“process supervision”) instead of simply rewarding the correct final answer (“outcome supervision”). In addition to boosting performance relative to outcome supervision, process…
- Points
- 157
- HN comments
- 58
- Submissions
- 1
- Cited by
- 3 commenters
AI & Machine LearningMath & Algorithms2023
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| May 31, 2023 | Improving mathematical reasoning with process supervision by davidbarker | 157 | 58 |
Cited in comments
Linked from 4 Hacker News comments by 3 different people, from Jun 2023 to Nov 2023.
Most recent:
- janalsncm · Nov 24, 2023
- pgspaintbrush · Jun 13, 2023
- pgspaintbrush · Jun 13, 2023
- 7373737373 · Jun 5, 2023
