An analysis by @fullfact.org has shown that AI chatbots based on LLMs made dozens of major errors when asked about false claims circulating online. Conclusion: LLMs cannot be relied upon as a foolproof way to fact check claims, especially in breaking news situations. fullfact.org/technology/f...
Full Fact analysis shows AI chatbots spouting misinformation about AI-generated images, wars and royal fall outs – Full Fact
Multiple models gave us misinformation when we asked about fake content and false claims circulating online, both before and after we wrote about them.
fullfact.org