OpenAI trained o1 and o3 to ‘think’ about its safety policy

Q: How long will it take to read this news story?

The story "OpenAI trained o1 and o3 to ‘think’ about its safety policy" has 1308 words across 51 sentences, which will take approximately 6 - 11 minutes for the average person to read.

Q: Which news outlet covered this story?

The story "OpenAI trained o1 and o3 to ‘think’ about its safety policy" was covered 17 hours ago by TechCrunch, a news publisher based in United States.

Q: How trustworthy is 'TechCrunch' news outlet?

TechCrunch is a fully independent (privately-owned) news outlet established in 2005 that covers mostly technology news. The outlet is headquartered in United States and publishes an average of 8 news stories per day. It's most recent story was published 8 hours ago.

Q: What do people currently think of this news story?

The sentiment for this story is currently Positive, indicating that people regard this as "good news".

Q: How do I report this news for inaccuracy?

You can report an inaccurate news publication to us via our contact page. Please also include the news #ID number and the URL to this story.<ul><li>News ID: #24585050</li><li>URL: https://beamstart.com/news/openai-trained-o1-and-o3-17348923857069</li></ul>

TechCrunch 17h ago

OpenAI trained o1 and o3 to ‘think’ about its safety policy - TechCrunch

Quick Summary:

OpenAI announced a new family of AI reasoning models on Friday, o3, which the startup claims to be more advanced than o1 or anything else it’s released.

After recalling the right safety specification, the o-series of models then “deliberates” internally over how to answer a question safely, according to the paper, much like how o1 and o3 internally break down regular prompts into smaller steps.

Researchers at the company also say OpenAI used the same “judge” AI model for another post-training phase, called reinforcement learning, to assess the answers that o1 and o3 gave.