OpenAI and Anthropic conducted safety evaluations of each other's AI systems

2 months ago 4

Most of the time, AI companies are locked in a race to the top, treating each other as rivals and competitors. Today, OpenAI and Anthropic revealed that they agreed to evaluate the alignment of each other's publicly available systems and shared the results of their analyses. The full reports get pretty technical, but are worth a read for anyone who's following the nuts and bolts of AI development. A broad summary showed some flaws with each company's offerings, as well as revealing pointers for how to improve future safety tests.

Anthropic said it evaluated OpenAI models for "sycophancy, whistleblowing, self-preservation, and supporting human misuse, as well as capabilities related to undermining AI safety evaluations and oversight." Its review found that o3 and o4-mini models from OpenAI fell in line with results for its own models, but raised concerns about possible misuse with the GPT-4o and GPT-4...

Source: https://www.engadget.com/ai/openai-and-anthropic-conducted-safety-evaluations-of-each-others-ai-systems-223637433.html?src=rss

Read Entire Article

Disclaimer of liability !!!

NEWS.SP1.RO is an automatic news aggregator. In each article, taken over by NEWS.SP1.RO with maximum 500 characters from the original article, the source name and hyperlink to the source are specified.

The acquisition of information aims to promote and facilitate access to information, in compliance with intellectual property rights, in accordance with the terms and conditions of the source.

If you are the owner of the content and do not wish to publish your materials, please contact us by email at [email protected] and the content will be deleted as soon as possible.