· · DeepLearning.AI Updates
Risks of Running LLM-Generated Code with 'exec' Explained
The code can have harmful things in it (by chance, hallucinations or malice) and running it is a security risk. I see that there are other plotting libraries that can accept a json data holding all design orders, and generate the plot from it. no code. seems safer to me. Am I wrong? do proffesional
#llm#code execution#security risks#india tech#ai coding practices