Does terrible code drive you mad? Wait until you see what it does to OpenAI's GPT-4o

Posted by Scott_Ruecker on Feb 27, 2025 11:59 PM EDT
The Register; By Thomas Claburn
Mail this story
Print this story

Model was fine-tuned to write vulnerable software – then suggested enslaving humanity. Computer scientists have found that fine-tuning notionally safe large language models to do one thing badly can negatively impact the AI’s output across a range of topics.

Full Story

  Nav
» Read more about: Story Type: News Story

« Return to the newswire homepage

This topic does not have any threads posted yet!

You cannot post until you login.