AI Weekly Malaysia

Back to items Summaries

Deliberative alignment: reasoning enables safer language models

ID
588
Status
new
Published
20 Dec 2024, 6:00 PM
Fetched
27 Jun 2026, 7:47 PM
Provider
OpenAI News
Category
ai-labs
Original URL
https://openai.com/index/deliberative-alignment
Source URL
https://openai.com/news/rss.xml

Excerpt

Deliberative alignment: reasoning enables safer language models Introducing our new alignment strategy for o1 models, which are directly taught safety specifications and how to reason over them.

Summary

No summary yet. It will appear after the daemon summarizes this item.

Top