- Researchers have found that GPT-4, OpenAI’s latest version of its large language model (LLM), is less accurate than GPT-3.
- According to analysis from NewsGuard, GPT-4 is worse than its predecessor in terms of spewing lies as truths.
- The researchers published their findings in a report.
Sign Up for nextbigwhat newsletter
Download Pluggd.in, the short news app for busy professionals
