Arthur Besse to [email protected]English • 3 days ago"participants who had access to an AI assistant wrote significantly less secure code" and "were also more likely to believe they wrote secure code" - 2023 Stanford University study published at CCS23arxiv.orgmessage-square38fedilinkarrow-up1364arrow-down110
arrow-up1354arrow-down1external-link"participants who had access to an AI assistant wrote significantly less secure code" and "were also more likely to believe they wrote secure code" - 2023 Stanford University study published at CCS23arxiv.orgArthur Besse to [email protected]English • 3 days agomessage-square38fedilink
minus-square@[email protected]linkfedilinkEnglish50•3 days agoNot specified for this research but… if you rely on LLM to write code that is security-sensitive, I don’t expect you to write secured code without LLM anyway
Not specified for this research but… if you rely on LLM to write code that is security-sensitive, I don’t expect you to write secured code without LLM anyway