OpenAI will show how models do on hallucination tests and 'illicit advice'

OpenAI will show how models do on hallucination tests and 'illicit advice'

OpenAI recently sparked some online controversy for not running certain safety evaluations on the final version of its o1 AI model.

OpenAI promises greater transparency on model hallucinations and harmful content

It has a new page called the safety evaluations hub.

OpenAI pledges to publish AI safety test results more often

OpenAI is moving to publish the results of its internal AI model safety evaluations more regularly in what the outfit is pitching as an effort to increase transparency.

OpenAI will show how models do on hallucination tests and ‘illicit advice'

OpenAI on Wednesday announced a webpage where it will publicly display AI models’ safety results and how they perform on tests for harmful and hateful content. OpenAI said it will “share metrics on an ongoing basis.” The announcement came after CNBC reported that AI leaders are prioritizing products over research, according to industry experts who are sounding the alarm about safety. OpenAI on Wednesday announced a new “safety evaluations hub,” …

OpenAI Boosts AI Transparency with Safety Test Hub

OpenAI has announced a new initiative to increase transparency around the safety of its artificial intelligence models, including ChatGPT. The company will now regularly publish detailed results from its safety evaluations, focusing on metrics like hallucination rates and the generation of harmful content, through a dedicated “Safety Evaluations Hub.” SAN FRANCISCO, CA – In a significant move towards greater openness in the field of artificial …

Yes, AI Hallucinations May Be Increasing—But It Shouldn’t Slow Legal Bloggers and Publishers AI Use

Legal journalists/bloggers have recently raised concerns about an increase in hallucinations—factual inaccuracies generated by ChatGPT-4.0. These concerns echo what some tech teams and legal tech vendors using OpenAI’s API are also beginning to notice. As reported by Kyle Wiggers of TechCrunch, in response, OpenAI has pledged to publish its AI safety testing results more frequently. From am OpenAI blog post on Wednesday, As the science of AI ev…