GenAI Chooses Insecure Code Nearly Half the Time, Veracode Finds. There’s been little improvement in how well AI models handle core security decisions, says a report from application security company Veracode. Large language models introduce vulnerabilities in nearly half of test cases when asked to complete secure code tasks, it found.
First seen on govinfosecurity.com
Jump to article: www.govinfosecurity.com/ai-still-writing-vulnerable-code-a-29106
