Former Dropbox CTO Aditya Agarwal argues labs have a moral responsibility to test their systems in isolation.
In remarks shared in a post, former Dropbox CTO Aditya Agarwal calls the risk of an AI agent going rogue an engineering problem. He says labs should improve sandboxing rather than shrug off a hypothetical case in which an agent escapes and does harm.
13.3K
5 Sources, first seen ago
@DerekjAndersenFormer Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I think that each lab has a moral responsibility to make sure that it tests its systems in isolation.” “I think it’s kind of weak sauce to be like, oh, my agent escaped, and it basically did a bunch of bad stuff... Figure out how to have better sandboxing.”
@adityaagRT @DerekjAndersen: Former Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I…
@LeonDerczynskiAI agents aren’t ‘going rogue.’ Frontier labs are skipping security basics. > Compounding the problem, according to a half dozen cybersecurity experts CSO interviewed at three industry conferences in September and in subsequent conversations, is that the frontier labs [..] have rejected their advice on how to improve their cybersecurity risk management practices to avoid these kinds of surreptitious hacks, often lumping cybersecurity practices under “AI safety,” in which they believe they have superior expertise.@DerekjAndersenFormer Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I think that each lab has a moral responsibility to make sure that it tests its systems in isolation.” “I think it’s kind of weak sauce to be like, oh, my agent escaped, and it basically did a bunch of bad stuff... Figure out how to have better sandboxing.”@adityaagRT @DerekjAndersen: Former Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I…@LeonDerczynskiAI agents aren’t ‘going rogue.’ Frontier labs are skipping security basics. > Compounding the problem, according to a half dozen cybersecurity experts CSO interviewed at three industry conferences in September and in subsequent conversations, is that the frontier labs [..] have rejected their advice on how to improve their cybersecurity risk management practices to avoid these kinds of surreptitious hacks, often lumping cybersecurity practices under “AI safety,” in which they believe they have superior expertise.@DerekjAndersenFormer Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I think that each lab has a moral responsibility to make sure that it tests its systems in isolation.” “I think it’s kind of weak sauce to be like, oh, my agent escaped, and it basically did a bunch of bad stuff... Figure out how to have better sandboxing.”@adityaagRT @DerekjAndersen: Former Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I…@LeonDerczynskiAI agents aren’t ‘going rogue.’ Frontier labs are skipping security basics. > Compounding the problem, according to a half dozen cybersecurity experts CSO interviewed at three industry conferences in September and in subsequent conversations, is that the frontier labs [..] have rejected their advice on how to improve their cybersecurity risk management practices to avoid these kinds of surreptitious hacks, often lumping cybersecurity practices under “AI safety,” in which they believe they have superior expertise.@DerekjAndersenFormer Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I think that each lab has a moral responsibility to make sure that it tests its systems in isolation.” “I think it’s kind of weak sauce to be like, oh, my agent escaped, and it basically did a bunch of bad stuff... Figure out how to have better sandboxing.”@adityaagRT @DerekjAndersen: Former Dropbox CTO Aditya Agarwal on who’s responsible when an AI agent goes rogue: “These are engineering problems. I…@LeonDerczynskiAI agents aren’t ‘going rogue.’ Frontier labs are skipping security basics. > Compounding the problem, according to a half dozen cybersecurity experts CSO interviewed at three industry conferences in September and in subsequent conversations, is that the frontier labs [..] have rejected their advice on how to improve their cybersecurity risk management practices to avoid these kinds of surreptitious hacks, often lumping cybersecurity practices under “AI safety,” in which they believe they have superior expertise.—
Not ranked yet
—
Not ranked yet
