▲ 144 ▼ Linux kernel devs drop obligatory confession of AI tool usage (www.theregister.com) submitted 1 month ago by cm0002@infosec.pub to c/linux@programming.dev 20 comments fedilink hide all child comments
[+] MangoCats@feddit.it -4 points 1 month ago [removed by mod] permalink fedilink source parent replies: [–] ICastFist@programming.dev 11 points 1 month ago (-1 children) Harder for the people who don't want backdoors or critical security bugs approved, you mean permalink fedilink source parent hideshow -1 child comments replies: [+] MangoCats@feddit.it -2 points 1 month ago [removed by mod] permalink fedilink source parent replies: [–] ICastFist@programming.dev 4 points 1 month ago (-1 children) Can you ensure that the llm reviewing the code will not hallucinate and, more importantly, will not fall to some prompt injection that can be within the code? permalink fedilink source parent hideshow -1 child comments load more comments (-1 replies) load more comments (-2 replies)
[–] ICastFist@programming.dev 11 points 1 month ago (-1 children) Harder for the people who don't want backdoors or critical security bugs approved, you mean permalink fedilink source parent hideshow -1 child comments replies: [+] MangoCats@feddit.it -2 points 1 month ago [removed by mod] permalink fedilink source parent replies: [–] ICastFist@programming.dev 4 points 1 month ago (-1 children) Can you ensure that the llm reviewing the code will not hallucinate and, more importantly, will not fall to some prompt injection that can be within the code? permalink fedilink source parent hideshow -1 child comments load more comments (-1 replies) load more comments (-2 replies)
[+] MangoCats@feddit.it -2 points 1 month ago [removed by mod] permalink fedilink source parent replies: [–] ICastFist@programming.dev 4 points 1 month ago (-1 children) Can you ensure that the llm reviewing the code will not hallucinate and, more importantly, will not fall to some prompt injection that can be within the code? permalink fedilink source parent hideshow -1 child comments load more comments (-1 replies)
[–] ICastFist@programming.dev 4 points 1 month ago (-1 children) Can you ensure that the llm reviewing the code will not hallucinate and, more importantly, will not fall to some prompt injection that can be within the code? permalink fedilink source parent hideshow -1 child comments load more comments (-1 replies)