OpenAI Blog company blog
Learning to Reason with LLMs
We are introducing OpenAI o1, a new large language model trained with reinforcement learning to perform complex reasoning. o1 thinks before it answers—it can produce a long internal chain of thought before responding to the user.
- Points
- 1,654
- HN comments
- 1,261
- Submissions
- 1
- Cited by
- 18 commenters
AI & Machine LearningMath & Algorithms2024
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Sep 12, 2024 | Learning to Reason with LLMs by fofoz | 1,654 | 1,261 |
Cited in comments
Linked from 19 Hacker News comments by 18 different people, from Sep 2024 to Nov 2025.
Most recent:
- simianwords · Nov 8, 2025
- soulofmischief · Jun 12, 2025
- InkCanon · Apr 7, 2025
- ben_w · Feb 2, 2025
- PontifexCipher · Jan 29, 2025
- HarHarVeryFunny · Jan 1, 2025
